arXane › Computer Science › Computer Science
Wednesday, 4 November 2026: 10 new papers, 4 cross-lists and 7 replacements in Computational Engineering, Finance, and Science (cs.CE), in arXiv's order, with full abstracts. The same papers as arXiv's own listing, set as a newspaper; every title links to arXiv.
Protein-protein interactions underpin nearly all biological processes. Yet, designing proteins with desired interactions remains challenging due to the structural complexity governing molecular recognition. This study views protein design as a search optimization problem over a combinatorial sequence space under expensive structural evaluation. Toward this goal, we introduce a novel tree-based search framework, ProteoCraft, that employs approximate structural gradients from diffusion-based structure predictors as effective proposal policies to specify where the search should explore. Complete no-gradient inference of folding models separately assigns values to the resulting sequences, determining what is good. ProteoCraft allocates this verification budget through a coarse-to-fine paradigm: multi-site edits first explore distinct sequence basins, then verified promising states undergo strict single-site refinement. Across fourteen de novo binder-design settings spanning eight target proteins, five immune-relevant TCR-facing targets, and four localized CDR redesign tasks, ProteoCraft improves design quality and high-confidence yield. These improvements persist under independent AF2-IG and Rosetta-based interface evaluation. Prospective experimental validation further yielded an 82.9% binding hit rate for PD-L1 miniproteins, with a best measured KD of 0.879 nM, and confirmed binding of designed IFNAR2 VHH. Our code is available at https://github.com/smiles724/ProteoCraft_v1.
When an industrial control system misbehaves, the defender often must choose between acting now on the most likely cause and first gathering evidence that separates two look-alike causes, while the process drifts toward a shutdown. Learning or evaluating such decisions requires the cost of every candidate action from the same situation, which no public cyber-physical security dataset provides. We present TE-GvA, a counterfactual decision dataset for fault-driven incident response on the revised Tennessee Eastman process, with 9,908 decision points from 1,990 simulated incidents, each with 4 to 35 candidate actions labelled by branched rollouts with common random numbers. Labels computed under the true hidden cause (hindsight labels) make gathering the best choice in only 1.1-1.3% of decisions. For the dominant look-alike pair, a failed network link versus a frozen I/O module, we add pair-conditioned belief labels from twin episodes that replay the defender's history under the other cause, weighted by the exact posterior. With them, gathering is best in 15.5% of ambiguous natural decisions and in 33.1% of ambiguous stress decisions without a backup channel. When the posterior is correct and the twin is faithful, belief labels have the same regression target as hindsight labels and lower variance. In a pre-specified, single-look test evaluation, a gradient-boosted rule trained on belief labels has 11% lower regret on the stress set than the same rule trained on hindsight labels, and 27% lower regret on ambiguous stress decisions without a backup channel, which remains significant after Holm correction. With a backup channel and in the natural distribution, the two label sets perform about the same. Soft labels tolerate moderate posterior errors, whereas hard labels that commit to one cause do worse than hindsight labels.
An engineering solver can converge even when a language agent has misread the user's problem. AgenticTO makes this distinction inspectable by keeping three records separate: the proposed problem specification, deterministic formulation checks, and numerical acceptance of the solved design. We evaluated the workflow on 50 author-built topology-optimization briefs, injected faults, five numerical problems, and complete agent sessions. The tests used linear-elastic models with one load case. Geometry tools raised the primary provider's correct specifications and refusals from 37 to 44 of 50, while also increasing wrong specifications delivered as finished. Input-format feedback alone recovered most of the accuracy gain. The wrong specifications passed the formulation rules, which also missed most injected faults that changed the intended problem. Clarification corrected the remaining errors when an oracle supplied reference facts, but also prompted questions on fully specified briefs. Perfect accuracy under that oracle therefore does not establish performance with engineers. Numerical trials reached 73.7 million elements, although released designs used finer grids than requested. The records expose how a proposed problem becomes an accepted numerical result; agreement with the brief still needs a separate judgment.
LLMs are increasingly adopted to draft long-form investment research memos, but their reliability is judged claim by claim, while readers read each memo as a whole. In this paper, we show that a low claim-level error rate does not necessarily mean that a memo is reliable: even with a refutation rate of just 1-2%, roughly four in ten memos contain at least one claim contradicted by official filings. First, we generate 1,440 memos with four recent LLM-powered agents for 30 companies over 12 quarters, decompose them into 77,272 financial claims, and verify each against the same official source bundle by retrieving evidence, matching it to the claim, and verifying the outcome. Second, we find that only 1.17-1.77% of claims are refuted, yet 36.94-41.11% of memos contain at least one refuted claim, and agents differ in severity: Codex has the lowest memo-level rate; a qualitative review further groups errors into four patterns (time, unit, context, concept).
Data products are non-standardized and context-dependent, so their prices are jointly shaped by product attributes and contextual factors such as provider reputation, product comparability, and industry structure. We formulate data product pricing as a learning task over a heterogeneous information network spanning data products, providers, marketplaces, industries, and pricing modes, and design theory-grounded meta-paths, brand-based, similarity-based, industry-based, and hybrid, to characterize distinct pricing mechanisms. Building on this network, we propose a Meta-Path-Guided Heterogeneous Graph Neural Network (MPGNN), which learns path-specific representations, fuses them through an attention-based gate, and is further augmented with large language model-generated textual features. Empirical evaluation shows that MPGNN achieves statistically significant improvements over baseline models in both regression and classification across different pricing modes, and that provider-involving meta-paths dominate the learned weights, yielding predictive evidence consistent with a brand-equity-related pricing mechanism. The proposed framework combines predictive accuracy with theory-driven interpretability, offering a transferable methodological template for pricing other non-standardized digital assets.
This work presents a new method for gradient-based optimization of the rhombic transposition flap and the excision it closes, which set the strain of the skin after closure. Previous studies swept at most three parameters. Here, using structural optimization methods, up to eight variables, two flap angles, two cut lengths and the size, shape and position of the rhombic excision, are optimized under up to 32 geometric and stress constraints. The skin is a pre-stretched, incompressible hyperelastic membrane that wrinkles instead of carrying compression. Smoothed level-sets on a fixed grid represent the cuts, and springs between interpolated points the sutures, so designs change without remeshing and the adjoint method gives the sensitivities. The energy the surgery adds to the skin is minimized, and the model reproduces the energies of a published 48-design sweep with a median deviation of 5%. The optimal flap angles, $(-23^\circ, 31^\circ)$, lie outside the swept range and add 63% less energy than the Limberg flap and 15% less than the best swept design. Under unequal in-vivo tension, the optimal flap turns with the direction of the tension. Fitting the excision to the lesion and its margin lowers the energy by a further 35%, and with all eight variables it is 78% below the Limberg flap. This optimum is the same for finer grids, narrower cuts and wider undermining, although wider undermining reduces its gain. Lowering its suture-line stress by 41% costs only 2.3% more energy.
Koopman operator theory provides a principled framework for reduced-order modeling of nonlinear spatiotemporal dynamics through linear evolution in an observable space. In practice, however, learned finite-dimensional representations are typically approximately invariant, causing unresolved dynamics and accumulated closure errors. Recent approaches, inspired by the Mori-Zwanzig formalism, address these effects through deterministic memory or closure modeling, yet robust extrapolation beyond the training horizon remains challenging. Here, we propose KoopFlow, an efficient prediction-correction framework based on the key insight that finite-dimensional Koopman error accumulation can be reinterpreted as a progressive distributional degradation process. Accordingly, KoopFlow treats Koopman predictions as noisy intermediate estimates, which are then transported toward the target latent distribution through a generative model, thereby mitigating accumulated errors while retaining computational efficiency and temporal flexibility. Moreover, we reveal a non-monotonic relationship between Koopman spectral coherence and predictive accuracy. Experiments across diverse nonlinear dynamical systems demonstrate improved long-horizon prediction accuracy and stability over representative baselines, particularly beyond the training horizon.
Instrumented indentation enables assessment of local mechanical properties in heterogeneous polymer systems, but specimen preparation and the selected indentation protocol significantly influence the quantitative interpretation of the measured response. This study develops and evaluates an experimental methodology for spatially resolved mesoscale characterization of both unreinforced and short fiber-reinforced composites. An unreinforced material system is used as a reference material to systematically examine the effects of indentation spacing, surface preparation, maximum indentation load, temporal loading parameters, and unloading evaluation. Indentation loads of 500, 1000, and 1750 mN are investigated in complementary experimental campaigns. The apparent indentation modulus exhibits moderate sensitivity to indentation load and loading time within the studied ranges. In contrast, indentation depth and the creep-related depth increment display greater sensitivity to the applied load history. Surface polishing minimizes topographical disturbances and enables reliable identification of residual indentation profiles and pile-up. Based on these methodological findings, a final load-hold-unload protocol with an indentation load of 1750 mN, a loading time of 6 s, a holding period of 300 s, and an unloading time of 4 s is applied to both unreinforced material and short fiber-reinforced composites. The mean apparent indentation modulus increases from 2.91 GPa for unreinforced material to 6.65 GPa for short fiber-reinforced composites, while the mean depth of indentation creep decreases from 2.36 to 1.91 microns. The coefficient of variation also increases for both quantities, indicating that short-fiber reinforcement enhances mean local stiffness and introduces pronounced spatial heterogeneity in both stiffness-related and time-dependent mesoscale indentation responses.
Periodic composites with cohesive interfaces and matrix plasticity require nonlinear cell solutions in multiscale analysis. Process-zone condensation eliminates the linear elastic remainder of the cell by a Schur complement, retaining all interfacial and process-zone internal variables. Influence matrices recover macroscopic stress and consistent tangent. One back-substitution per increment checks that the matrix outside the retained zone remains elastic. While this holds, the reduction is exact relative to the full discretisation, also with a plastic matrix, and requires no training. In an E-glass/epoxy cell, eight of nine two-dimensional paths agree with the full cell to 1e-11 in stress and tangent; the check flags the ninth. Three paths on each of two three-dimensional meshes need zone expansion. Excluding setup and checks, two-dimensional path timings show an aggregate speed-up of 3.3; certified three-dimensional zones show none. In adaptive finite element squared (FE$^2$) simulations of a perforated plate, the reduced solver reproduces the full-cell response within solver tolerances, 1.51 times faster for glass/polypropylene and slower for glass/epoxy. Independent Ansys models agree to below 1e-3 in cell stress and about 0.6% in plate reactions, although local damage and plasticity onsets differ. The advantage depends on zone size, active set and adaptation costs.
Risk and reliability analysis are fundamental to the design, assessment, and operation of safety-critical complex systems; however, their integration into next-generation computational tools is constrained by the cost of uncertainty quantification with expensive computational models. The computational challenge is particularly prohibitive for tail-sensitive quantities, such as probabilities of failure, conditional values-at-risk, and buffered probabilities of failure, where accurate estimation can require a large number of model evaluations. Multifidelity methods provide a framework for addressing this computational bottleneck by combining information from models of varying accuracy and cost while retaining the predictive accuracy of the high-fidelity model. This review summarizes the state of the art in methods that enable scalable risk and reliability analysis using multifidelity control variates, multifidelity importance sampling, and multifidelity active learning.
Foundation machine-learning interatomic potentials (MLIPs) offer one model for many chemistries, but their deep, globally coupled architectures do not fit the spatial decomposition that scales classical and short-ranged MLIPs. We present pair_style uma, a LAMMPS pair style that evaluates the Universal Model for Atoms (UMA) through LibTorch on NVIDIA and Intel GPUs from a single source tree. It reimplements FairChem's edge-sharded graph parallelism in C++ over exported TorchScript modules, with one MPI rank per device, NCCL or oneCCL collectives, and the whole energy and force path in double precision. The strain-gradient virial is carried through the exported modules and the cross-device reductions, so that fix npt runs on both vendors' hardware. We measure NPT capacity and cost on one 4xA100-40GB node, one 8xH200 node, and one 12-tile Intel node, and on up to 32 Intel nodes. Without activation checkpointing, one node holds NaCl cells of about 8,000 atoms (A100, 0.21 ns/day), 22,000 atoms (Intel, 0.10 ns/day), and 47,000 atoms (H200, 0.16 ns/day). Graph parallelism raises the capacity of a single device by 8.0x on H200 and 4.6x on A100. Across nodes, capacity grows to about 779,000 atoms on 32 Intel nodes, with a slower speed at 0.007 ns/day. On H200 and A100, a FLOP count of FairChem's graph-parallel predictor gives lower bounds of 31% and 51% of FP64 peak. From one omat checkpoint and with no refit, nine 100 ps NPT heating ramps (NaCl, equiatomic Pt-Ru, and equiatomic (HfNbTaTiZr)N, on all three node types) ran to completion.
Prestress governs the stability, stiffness, and dynamic behavior of tensegrity structures, but it is not directly observable from sparse structural measurements, and it may decrease during service life. Under strong excitation, the cables may slacken and the dynamics become nonsmooth. Existing identification methods are limited to the taut regime, and physics-informed networks for tensegrities solve only the forward problem of predicting the response from known member parameters. This study formulates the inverse problem. Neural networks are trained on the equation-of-motion residual in constrained Cartesian coordinates, where the mass matrix is constant and the force densities enter linearly. The force densities, damping, and axial stiffness are trainable parameters, and the tension-only cable law is kept. A Fisher-information analysis shows, before inversion, which member parameters a record can determine. The method is tested on simulated planar tensegrity frames with up to five modules and a three-dimensional prism, and on measured records of a biomimetic leg and a full-scale tensegrity simplex. On the one-module frame, the identifiable force densities are recovered within 1.5% from noisy accelerations at half the free coordinates, on records with and without taut-slack transitions. Records with transitions determine members that taut records leave undetermined. On the five-module frame, a 16-cable two-span bridge, the median force-density error rises moderately, to 4.2%. On measured records, an identified spring stiffness is within 0.1% of its independently measured value on average, and the identified simplex prestress at 13 levels agrees with its cable force transducers to 2.9% root-mean-square.
Portfolio use of machine predictions must often proceed while the predictions' economic direction, reliability, and timing remain untrusted, and while feedback from overlapping multi-period positions arrives with delay. A controller chooses among Safe, Follow, and Reverse portfolio actions, so signal orientation is learned rather than assumed. A share-adaptive master updates action probabilities from matured Safe-relative rewards, an evidence gate can abstain by transferring unsupported directional probability to Safe, a delayed collateral budget reserves worst-case loss capacity before exposure is funded, and a protected split account caps the capital adaptive decisions may touch. The architecture carries a dual certificate, tracking regret against switching action sequences under delay and one-sided intervention, together with a pathwise collateral safety bound that holds when predictions fail. On a 24-stock development universe a conservative prediction-assisted overlay stays near equal-weight performance at a fraction of the turnover. On a frozen 82-stock holdout, the pre-specified Reverse orientation fails to outperform Equal Weight; a separately labeled post-holdout diagnostic shows that permanently flipping the sign to Follow also does not recover a return edge. Under the post-holdout controller, protected wealth remains within 15.9 basis points of the Safe benchmark throughout. The contribution is safe adaptive use of untrusted predictions, not demonstrated alpha.
Predicting affinity between small molecules and their protein targets remains one of the central problems in drug discovery. Due to the substantial cost of wet-lab experiments, machine learning models of drug-target affinity are usually trained on relatively small datasets, ranging from tens to hundreds of molecules. Given the inherent difficulty of generalization between different targets and chemical series, existing datasets of protein-ligand affinities are typically not used for new projects. At the same time, tabular foundation models, including Prior-data Fitted Networks, have recently shown how transformers can be used to solve machine learning problems in a single forward pass of the network, after being trained over a large corpus of, typically, synthetic datasets. Inspired by that line of work, we propose a novel affinity modelling approach, in which the labels of the query molecules are predicted from the labelled support molecules in a single forward pass of a transformer model. The model is trained on thousands of existing affinity datasets, enabling it to capture the general patterns of molecular activity across different targets, chemical series and dataset sizes. For the smallest support sets, our model matches the state of the art on the regression variant of the FS-Mol benchmark, while being faster than existing methods, thanks to the lack of task-specific training. A comparison against a reduced variant of our architecture, which amounts to kernel regression in a meta-learned feature space, shows that the predictive performance of the transformer model is only partially explained by simple molecular similarity.