{"total":14,"items":[{"citing_arxiv_id":"2606.24691","ref_index":224,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Learning Nonlinear Dynamics: Improving the Estimation Efficiency and Reliability of Gaussian Process State-Space Models","primary_cat":"stat.CO","submitted_at":"2026-06-23T15:19:14+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Modifies Gibbs sampler for GP state-space models, introduces CFA measurement structure, and validates software via simulation-based calibration to enable reliable learning of nonlinear latent dynamics.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.23575","ref_index":51,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Solve for the Hyperparameter, Skip the Search: Kolmogorov-Optimal Scaling Laws for Spline Regression","primary_cat":"cs.LG","submitted_at":"2026-06-22T16:41:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Kolmogorov n-width theory plus PRESS statistics yield closed-form optimal spline resolution; KORE estimates bias/noise scales from two pilots and matches CV performance with far fewer fits.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.21755","ref_index":39,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"RoverDevKit: An open, physics-grounded tradespace toolkit for conceptual design of lunar micro-rovers","primary_cat":"cs.RO","submitted_at":"2026-06-19T21:14:07+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"RoverDevKit is an open physics-based evaluator for lunar micro-rover conceptual design that runs in 30 ms and uses NSGA-II to identify mission-dependent optimal wheel configurations and binding trades.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.07982","ref_index":29,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Overcoming the Limits of Finite Difference Method; Physics-Informed Neural Network for Noisy High-Dimensional Heat Diffusion","primary_cat":"cs.LG","submitted_at":"2026-06-06T05:13:47+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"PINN achieves 91% accuracy in 3D noisy heat diffusion vs 36% for FDM and 3.3x better error reduction in physical experiment, with efficiency gains in high dimensions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.07947","ref_index":166,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Bayesian Global Fr\\'echet Regression via Weak Conditional Expectations","primary_cat":"stat.ME","submitted_at":"2026-06-06T02:34:09+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A Bayesian global Fréchet regression method is introduced via a Fréchet Bayes rule that reduces the problem to scalar tasks, allows prior-data interpolation, and remains valid under moment conditions using weak conditional expectations.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.27968","ref_index":48,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Adapting Automotive Aerodynamics Surrogates to New Vehicle Families via Transfer Learning","primary_cat":"cs.CE","submitted_at":"2026-05-27T05:03:25+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"LoRA adapters enable a 61.47M-parameter aerodynamics Transformer pretrained on four vehicle families to adapt to a held-out fifth family with 20 samples, reaching R²=0.85 and outperforming full fine-tuning and from-scratch training with 3x more data.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.27942","ref_index":3,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Quantum principal component analysis without eigenvector recovery","primary_cat":"quant-ph","submitted_at":"2026-05-27T04:27:47+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Presents a quantum soft PCA framework with Fermi-Dirac filter for principal subspace scoring without eigenvector recovery, claiming dimension-independent sample complexity O(η^{-2}).","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.27850","ref_index":11,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"TCP-MCP: Landscape-Guided Co-Evolution of Prompts and Communication Topologies for Multi-Agent Systems","primary_cat":"cs.AI","submitted_at":"2026-05-27T02:06:58+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"TCP-MCP co-evolves prompts and topologies for multi-agent systems, reporting 82.66-96.61% accuracy on MMLU-Pro/MMLU/GSM8K while using up to 5.69x fewer tokens than debate baselines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12007","ref_index":45,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"A geometry-aligned multi-fidelity framework for uncertainty quantification of wildfire spread","primary_cat":"cs.CE","submitted_at":"2026-05-12T11:55:52+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A geometry-aligned bi-fidelity surrogate maps low- and high-fidelity wildfire solutions to a common domain for improved reduced-basis reconstruction, lower error near fronts, and practical uncertainty quantification.","context_count":1,"top_context_role":"method","top_context_polarity":"use_method","context_text":",: Page 4 of 21 A geometry-aligned multi-fidelity framework for uncertainty quantification of wildfire spread Figure 1:Schematic representation of the geometry-aligned bi-fidelity algorithm, including offline construction and online prediction stages across both the physical and reference domains. ThesamplingmethodmayrelyonLatinHypercubeSampling(LHS)[45],classicalMonteCarlo[46],orotherefficient strategies such as importance sampling [47] or adaptive/sequential sampling [48], provided that the selected points cover the region of interest𝐼𝑧. For each sampled realization𝐳∈ Γ, an LF simulation is performed, producing the corresponding final snapshot𝑣𝐿(𝐳). Collectively, these realizations form the LF snapshot matrix:"},{"citing_arxiv_id":"2605.10958","ref_index":41,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Multi-Fidelity Emulation of Atmospheric Correction Coefficients with Physics-Guided Kolmogorov-Arnold Networks","primary_cat":"physics.ao-ph","submitted_at":"2026-05-04T22:43:25+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"pKANrtm uses a physics-aware multi-fidelity KAN to emulate high-fidelity radiative transfer coefficients for atmospheric correction with superior accuracy and large speedups over direct libRadtran runs.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"image reflectance prediction problem and as an RTM-assisted emulation problem. Shah et al. [40] organized deep-learning atmospheric correction approaches into physics-supported, physics-aware, and physics-agnostic categories. Basener and Basener [27] compared Gaussian-process and deep-learning atmospheric correction models and emphasized the value of interpretable probabilistic modeling. More recently, Shah et al. [41] proposed a spatio-temporal atmospheric correction network, showing that temporal information can improve surface-reflectance prediction compared with purely spatial learning. These studies demonstrate the promise of data-driven atmospheric correction, but many of them https://doi.org/ Version May 13, 2026 submitted toRemote Sens. 5 of 22 predict reflectance directly rather than emulating the intermediate coefficients used by"},{"citing_arxiv_id":"2604.19290","ref_index":36,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Orthogonal reparametrization of the Nelson-Siegel-Svensson interest rate curve model: conditioning, diagnostics, and identifiability","primary_cat":"q-fin.CP","submitted_at":"2026-04-21T09:55:25+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Orthogonal reparametrization via QR decomposition renders NSS linear parameters uncorrelated with diagonal conditional Fisher information, providing a scalar identifiability diagnostic and closed-form finite-horizon orthogonal basis.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"β⊤(Φ⊤Φ)βupweights directions that are already well-determined while leaving the ill-conditioned directions relatively unpenalized-precisely the opposite of what is needed. The SVD analysis and numerical results favor standard ridge regression∥β∥2 for stabilizing the inner linear subproblem when regularization is needed, with the regularization parameterαchosen by generalized cross-validation [35]; recent work [36] shows that standard GCV can be biased in finite samples with corre- lated features. The orthogonal basis provides a complementary diagnostic: when|R44|is small, truncation to k= 3components (equivalent to model reduction from NSS to NS) is an effective alternative to continuous regularization. This connects to the truncated SVD approach for discrete ill-posed problems [37]."},{"citing_arxiv_id":"2604.18414","ref_index":58,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Balance-Guided Sparse Identification of Multiscale Nonlinear PDEs with Small-coefficient Terms","primary_cat":"cs.LG","submitted_at":"2026-04-20T15:31:47+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"BG-SINDy reformulates l0-constrained regression as term-level l2,0 regularization and uses progressive pruning guided by balance contributions to recover small-coefficient terms in multiscale PDEs.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"failed discovery of the correct equation structure. 3.2. Modified Burgers equation with vanishing hyperviscosity This example aims to highlight BG-SINDy's ability to discover governing equations that contain small-coefficient terms involving high-order deriva- tives. We consider the modified Burgers equation augmented with a vanish- ing hyperviscosity term [ 58, 59] (i.e., a fourth-order derivative with a small coefficient): ∂u ∂t + u ∂u ∂x − 0.5 ∂2u ∂x2 + ε ∂4u ∂x4 = 0, (x, t) ∈ Ω × [0, T ], (14) subject to the initial condition u(x, 0) = cos \u0010 x 16 \u0011 , x ∈ Ω, and periodic boundary conditions, where ε = 1 × 10−3, Ω = [0 , 32π], and T = 100. The dataset is generated by numerically solving Eq. ( 14) using a fourth-"},{"citing_arxiv_id":"2511.20183","ref_index":24,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Multi-fidelity Gaussian process regression for noisy outputs and non-nested experimental designs: a comparison between the recursive and non-recursive formulations","primary_cat":"stat.AP","submitted_at":"2025-11-25T11:06:08+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Recursive multi-fidelity GP regression with EM optimization trains faster than the coupled non-recursive Kennedy-O'Hagan approach on noisy non-nested data while delivering comparable predictions and uncertainty estimates.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"1906.11861","ref_index":6,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Relating Simple Sentence Representations in Deep Neural Networks and the Brain","primary_cat":"cs.CL","submitted_at":"2019-06-27T18:23:27+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"BERT activations show strongest correlation with MEG data for simple sentences; DNN representations generate synthetic brain data that improves stimuli decoding accuracy.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}