The temperature increase in the contact regions between solids in sliding contact has a huge influence on friction and wear. Here we test an analytical theory for the flash temperature, valid for randomly rough surface with multiscale roughness, by comparing the theory predictions with the experimental results of Sutter et al \cite{Sutter} for steel sliding on steel. The theory, which is based on the study of stress and temperature correlation functions, is valid for randomly rough surfaces with roughness on arbitrary many decades in length scale. Within the uncertainty of the experimental data (mainly the surface roughness power spectrum and the steel penetration hardness), there is good agreements between the theory and the experimental results.

We define the category of $G_2$-structures over a Riemannian 7-manifold $M$ and present an isomorphism between this category and a full subcategory of the category of octonion algebras over the ring of smooth real-valued functions $C^\infty(M)$ of the same manifold $M$. A classification of $G_2$-structures in the same metric class is shown to agree with a parametrisation of octonion algebras with isometric norm. A short study of the local structure of octonion algebras over $C^\infty(M)$ shows similarities to the theory of octonion algebras over $\mathbb{R}$. Thus, many of the results on real octonion algebras, and in general octonion algebras over rings, can be applied to $G_2$-structures viewed as octonion algebras, under the aforementioned isomorphism of categories.

Gravitational wave (GW) observations of binary black hole (BBH) mergers provide a unique opportunity to probe the nature of spacetime in the strong-field and dynamical regime. We present updated constraints on deviations from the Kerr metric using BBH inspirals from the fourth Gravitational-Wave Transient Catalog (GWTC-4). Building on our previous GWTC-3 analysis, we employ a theory-agnostic framework in which non-Kerr effects of the Johannsen metric are incorporated as parametrized corrections to the GW phase within the post-Newtonian framework. We perform Bayesian parameter estimation on a selected subset of GWTC-4 events to constrain the deformation parameters $α_{13}$ and $ε_3$, yielding significantly tighter bounds compared to earlier results. When varied individually, the deformation parameters are found to be consistent with zero, providing no evidence for departures from the Kerr geometry. Our results reinforce the validity of General Relativity, particularly the Kerr hypothesis, and highlight the progress enabled by GWTC-4.

A lot of research relies on data analysis scripts to process, clean, and visualize data. However, recent studies show that these scripts are often hard to comprehend and maintain, hindering reproducibility and reuse, accompanied by a lack of tool support for handling such scripts. In this work, we focus on the R programming language, addressing this problem by presenting flowR as an extension for the common data analysis IDEs Positron and VS Code. Alongside a previously presented static backward program slicer, flowR provides an overview of data analysis scripts, interactive graph visualizations, linting, and inline value annotations to support data analysts. FlowR incrementally analyzes R projects by intertwining interprocedural data- and control-flow analyses to build a comprehensive dataflow graph, incorporating R's dynamic and explorative features. Additionally, flowR offers a plugin system and interfaces, allowing the integration of further analyses, such as new linting rules or custom visualizations. Requiring an average of 576ms to calculate the full dataflow graph of real-world projects, this enables near real-time feedback. The demonstration video is available at https://youtu.be/hJzr-r-NmMg . For the full source code and extensive documentation, refer to https://github.com/flowr-analysis/flowr . To try the docker image, use `docker run --rm -it eagleoutice/flowr`.

Digital labor platforms are increasingly used to procure human input, ranging from annotating data and red-teaming AI models, to ride-sharing and food delivery. A central concern in such markets is the ability of platforms to suppress wages by exploiting the abundance of low-cost labor. To study this exploitation pattern, we introduce a novel posted-price procurement model with coverage objectives. A platform seeks to complete M tasks by posting prices to sequentially arriving workers, each of whom accepts a task if it exceeds their private cost. First, we show that under natural assumptions on the workers' estimated cost, there exists a simple pricing strategy for the platform to cover all M tasks with wait time O(M), while paying only a O(log(M)/M) fraction of the total cost of labor. This result highlights how platforms can exploit workers' uncertainty about the cost of labor to effectively suppress wages. Then, we study collective action as a lever to increase wages and promote welfare in digital labor markets. In particular, we show how a small coalition of targeted low-cost workers who commit to a price floor forces the platform's total spending from logarithmic to linear in M. In contrast, a randomly sampled coalition of equal size remains largely ineffective. We complement our theory with synthetic experiments, showcasing the benefits of collective action across different market regimes.

Two-dimensional materials are expected to play an important role in next-generation electronics and optoelectronic devices. Recently, twisted bilayer graphene and transition metal dichalcogenides have attracted significant attention due to their unique physical properties and potential applications. In this study we describe the use of optical microscopy to collect the color space of chemical vapor deposition (CVD) molybdenum disulfide ($\mbox{MoS}_2$), and the application of a semantic segmentation convolutional neural network (CNN) to accurately and rapidly identify thicknesses of $\mbox{MoS}_2$ flakes. A second CNN model is trained to provide precise predictions on the twist angle of CVD-grown bilayer flakes. This model harnessed a dataset comprising over 10,000 synthetic images, encompassing geometries spanning from hexagonal to triangular shapes. Subsequent validation of the deep learning predictions on twist angles was executed through the second harmonic generation and Raman spectroscopy. Our results introduce a scalable methodology for automated inspection of twisted atomically thin CVD-grown bilayer.

Many small-scale software systems, that is, with limited codebase or binary size, are widely used in everyday tasks, yet their configurability remains largely unexplored. At the same time, studies on modern software systems show a trend toward increasing configurability, alongside growing interest in building immutable, specialized, and reproducible software. In this paper, we present the first empirical study on the extent of configurability in small-scale software systems. By analyzing 108 programs from GNU coreutils, we show that even small programs can exhibit significant compile-time and run-time variability, with up to 76 options per program. Then, there is a high correlation (0.78) between run-time variability and codebase size. Furthermore, an analysis of the 20 smallest programs across 85 releases reveals that variability tends to increase over time, primarily due to the added compile-time variability. This suggests that shifting options between run-time and compile-time, removing unnecessary run-time variability, or resolving compile-time variability early, can help reduce codebase complexity and size. We also introduce, for the first time, the concept of null-variable software system, one with no configurability beyond mandatory features. Our findings show that high configurability is not exclusive to large-scale systems and that reducing unnecessary variability can lead to lightweight, smaller, and more maintainable software. We hope this effort contributes to designing new software by understanding how to balance its configurability with codebase size.

Ultra-massive multiple-input multiple-output (UM-MIMO) is a key technology for enabling terahertz (THz) communications in 6G networks, offering high beamforming gain to combat severe path loss. However, the large antenna array expands the near-field region, resulting in a hybrid near- and far-field communication environment. This makes channel estimation significantly more challenging than in conventional networks. To address this issue, we propose a novel attention augmented channel estimator named the fixed-point attention network (FP-ANet), which integrates fixed-point theory with a dual-attention mechanism. By combining a linear and dual-attention residual blocks based non-linear estimator in each iteration, this model-driven approach effectively exploits the sparsity of THz channels in the angular-distance domain, enabling a more precise and physically-grounded channel estimation. Simulation results show that FP-ANet achieves superior channel estimation accuracy compared to state-of-the-art methods while maintaining comparable computational complexity.

Particle-resolved direct numerical simulation (PR-DNS) is performed for turbulent open channel flow over a smooth horizontal wall with a vertical cylinder and a dilute set of mobile, heavy, spherical particles. At the chosen parameter point (which matches a previous study without a cylinder) the particles are mostly translating in the horizontal plane while remaining in contact with the wall. It is shown that the presence of the cylinder leads to the generation of intense vortical structures, enhanced turbulence intensity in the wake region, and to strong modifications of the local wall shear stress. These cylinder-induced perturbations have direct consequences for the average particle concentration: preferential accumulation/depletion in different parts of the wake region occurs, while the wall-normal transport of particles (against gravity) is significantly enhanced. A second simulation which adds roughness elements on the wall reveals an additional effect upon the wall-normal distribution of particles. It turns out that the configuration with wall-roughness and a wall-mounted cylinder features the largest fraction of entrained particles, even far from the wall.

In this paper, we investigate the long-time dynamics of a repulsive Keller-Segel chemotaxis system. The model features negative chemotaxis, logistic growth and a cell death term, accounting for a lethal chemorepellent that is self-produced by the cells and externally supplied. We prove that, for constant chemorepellent supplies, depending on their magnitude with respect to the logistic growth rate, solutions converge in $L^\infty$ norm toward extinction of the population, or equilibrate toward a nontrivial spatially homogeneous steady state.

While externally driven information engines are well understood, the thermodynamic constraints of their autonomous counterparts remain an open question. Here, we investigate the finite-time operation of an autonomous machine functioning as both an information eraser and a refrigerator, revealing that its irreversibility is bounded by the transient information geometry. Beyond steady-state boundaries, we map the landscape of optimal operation times across both functional modes, uncovering a unique synergistic regime where erasure power $P$ and efficiency $η$ increase simultaneously. Fundamentally, this performance is governed by a trade-off relation, $v(1-η)P/η\le D$, where $v$ is the operational speed and $D$ denotes an information-geometric distance. Our findings pave the way for optimizing fast autonomous information-energy conversion.

We derive the first two moments of generic positive stochastic functionals in terms of the one- and two-time probability density functions of the underlying random walk, and we prove ergodicity of observables in stationary random walks. These general results are applied to the half-occupation time and the occupation time in an interval of a Gaussian random walk, for which we obtain exact analytic expressions for the first two moments. We then extend the analysis to scaled Brownian motion and fractional Brownian motion, computing the ergodicity breaking parameter and establishing a simple scaling form for the probability densities of occupation times. Within the framework of infinite ergodic theory, we further identify universal properties of positive observables. All analytical predictions are fully confirmed by numerical simulations.

Richter, Stephan, and Zhang asked whether every nonrecursive many-one degree contains a least finite-one degree. We prove this for every nonrecursive \ce\ many-one degree containing a $D$-maximal set. The proof handles the simple cases via known results and develops a duplicate-cover method for the remaining $D$-maximal types in the classification of Cholak, Gerdes, and Lange.

We prove scattering for the defocusing energy-critical non-linear wave equation with Dirichlet boundary conditions outside two strictly convex obstacles in dimension three. This is the first large data scattering result for such an equation in the presence of trapped trajectories. Our result is in fact more general and can be used as a black box in other geometries. More precisely, under the assumptions that the corresponding linear wave equation satisfies global Strichartz estimates, that the domain is weakly non-trapping and that trajectories do not reconcentrate, we show linear and nonlinear profile decompositions in infinite time. This implies scattering under the rigidity assumption that the only compact-flow solution is the trivial one.

Masures are generalizations of Bruhat-Tits buildings adapted to the study of Kac--Moody groups over valued fields. They were introduced by Gaussent and Rousseau in 2007. Rousseau defined an axiomatic for these object and we simplified it. In this paper, which is mainly expository, we construct the masure associated with a split Kac--Moody group over a valued field, and we prove that it satisfies our axiomatic.

We extend the Kajueter-Kotliar [Phys. Rev. Lett. 77, 131 (1996)] iterated perturbation theory (KK-IPT) away from half filling to nonequilibrium steady states. We benchmark the resulting nonequilibrium KK-IPT approach against the auxiliary master equation approach (AMEA), whose accuracy is controlled in and out of equilibrium. As expected, in equilibrium, KK-IPT reproduces the AMEA results for different fillings with high accuracy at the level of both spectral properties and electron densities. Out of equilibrium, we study quantum transport across a correlated impurity and compute the differential conductance and spectral functions. We find very good agreement between nonequilibrium KK-IPT and AMEA in the parameter regime where the latter is reliable, in particular at moderate temperatures and biases. These results support nonequilibrium KK-IPT as an approximate description of nonequilibrium steady states away from half filling. Although a controlled benchmark is not available in the low-temperature, low-bias regime, where AMEA becomes less reliable, nonequilibrium KK-IPT remains numerically stable in those regions, suggesting that it may provide a useful alternative for nonequilibrium calculations in this regime.

Dense wireless deployments face co-channel interference from heterogeneous sources that vary across base stations (gNBs in 5G). While centralized DNN-based approaches to interference mitigation have shown strong performance, deploying and adapting these models across distributed gNBs via federated learning (FL) requires transmitting full model updates each round, resulting in a cost that scales poorly with network density. Parameter-efficient fine-tuning (PEFT) reduces this burden by training and communicating only a small fraction of parameters. While traditionally applied to large foundation models, we adapt Low-Rank Adaptation (LoRA) to temporal convolutional neural network architectures for interference suppression, placing low-rank adapters on the dilated convolutional layers. This placement enables LoRA to learn local interference-specific temporal patterns, while the frozen backbone retains the shared signal extraction capability. These lightweight adapters (5.1\% of backbone parameters) are federated via FedAvg, reducing per-round communication by up to 20$\times$ compared to federating full model updates. We evaluate various PEFT strategies across simulated distributed gNBs with non-IID interference environments. Results show that local LoRA achieves 12.8\% average BER improvement over the frozen backbone, while Fed-LoRA achieves comparable performance (12.6\%). Fed-LoRA outperforms local adaptation on data-starved nodes where federated knowledge transfer compensates for limited samples, all while avoiding the catastrophic degradation observed with full-model FedAvg under heterogeneous conditions.

Kagome metals are prone to charge-density wave (CDW), magnetic, and superconducting phases, with their flat electronic band conducive for correlated physics. In contrast to the weakly correlated $A$V$_3$Sb$_5$ ($A$ = K, Rb, Cs) kagome metals with a $2\times2$ CDW, CsCr$_3$Sb$_5$ is a correlated metal with a flat band close to the Fermi level, and exhibits a $4\times1$ CDW intertwined with magnetic order. Under pressure, the intertwined orders are suppressed and give way to a dome of superconductivity that emerges from a non-Fermi liquid normal state. Here, we solve the crystal structure of the $4\times 1$ CDW state in CsCr$_3$Sb$_5$, and show it consists of Cr dimers separated by Cr chains. First-principles calculations show the dominant exchange interaction is antiferromagnetic within the dimers, while the intra-chain and dimer-chain couplings are much weaker. The CDW transition of CsCr$_3$Sb$_5$ is found to be more strongly first-order than those in $A$V$_3$Sb$_5$, without significant soft phonons or diffuse scattering above the CDW transition temperature. These findings suggest that fluctuating antiferromagnetic dimers may play a major role in the electron pairing of superconducting CsCr$_3$Sb$_5$.

We present density response estimators for Monte Carlo simulations that are based on a reweighting procedure, where the samples of an unperturbed system are used to estimate the properties of a system perturbed by an external harmonic potential. This allows the linear and nonlinear static density response to be estimated purely from simulations of the unperturbed system. The method is demonstrated for the uniform electron gas under warm dense matter and strongly coupled conditions using ab initio path integral Monte Carlo simulations. The performance of the method with respect to the number of particles and the number of imaginary time slices is investigated. The scheme is generalised to consider multiple external perturbations, acting on different species and with different wavenumbers, giving one access to additional cross-species density response functions and the complete quadratic response function resolved for both wave number arguments through mode coupling. The flexibility of the methodology opens the possibility to investigate numerous new density response properties to further advance our understanding of interacting quantum many-body systems across a broad range of applications.

This paper studies an online trading variant of the classical secretary problem, called secretary problem variant trading (SPVT), from the perspective of an intermediary who facilitates trade between a seller and $n$ buyers (collectively referred to as agents). The seller has an item, and each buyer demands the item. These agents arrive sequentially in a uniformly random order to meet the intermediary, each revealing their valuation of the item upon arrival. After each arrival, the intermediary must make an immediate and irrevocable decision before the next agent appears. The intermediary's objective is to maximize the price of the agent who ultimately holds the item at the end of the process. We evaluate the performance of online algorithms for SPVT using two notions of competitive ratio: strong and weak. The strong notion benchmarks the online algorithm against a powerful offline optimum: the highest price among the $n+1$ agents. We propose an online algorithm for SPVT achieving a strong competitive ratio of $\frac{4e^2}{e^2+1} \approx 3.523$, which is the best possible even when the seller's price may be zero. This tight ratio closes the gap between the previous best upper bound of $4.189$ and lower bound of $3.258$. In contrast, the weak notion restricts the offline optimal algorithm to the given arrival order. The offline algorithm can no longer alter the predetermined arrival order to always place the item in the hands of the agent offering the highest price. Against this weaker benchmark, we design a simple online algorithm for SPVT, achieving a weak competitive ratio of $2$. We further investigate the special case in which the seller's price is zero. For this special SPVT, we develop a double-threshold algorithm achieving a weak competitive ratio of at most $1.83683$ and establish a lower bound of $1.76239$.

We investigate the ability of machine learning to infer the virial mass ($M_{\rm vir}$) and the scale radius ($r_{\rm s}$) of galaxy clusters from their observables. Using the Uchuu--UniverseMachine galaxy catalog at $z=0.093$, we generate mock cluster observations that include interlopers, and we encode each cluster as an image representing the two-dimensional joint probability distribution of member galaxies' projected position and line-of-sight velocity. We train two architectures: a baseline convolutional neural network (CNNb) following a previous approach, and an extended model (CNNr) that appends richness as an additional scalar input. We further compare the performance of networks trained on the all cluster sample and on a dynamically relaxed subsample. Across the test ranges $10^{13.7}\leq M_{\rm vir}\leq10^{15.3}$ Msun/h and $10^{1.7}\leq r_{\rm s}\leq10^{2.7}$ kpc/h, all configurations yield nearly unbiased absolute median residuals (within 0.01 dex). For the halo mass, adding richness narrows the residual distribution, reducing the standard deviation from 0.133 to 0.122 dex for the all sample, and from 0.124 to 0.111 dex for the relaxed sample. For the scale radius, restricting the training to relaxed clusters improves the performance more than adding richness. The standard deviation decreases from 0.180 to 0.154 dex for CNNb and from 0.175 to 0.148 dex for CNNr, while the inclusion of richness yields only a modest improvement of 0.005 dex. These results demonstrate that machine learning is a powerful tool to infer the mass and internal mass distribution of clusters, providing a new window for cosmological inferences and understanding galaxy formation processes.

Reactions occurring on the ice-covered surfaces of interstellar dust grains are considered to be among the most important sources of complex species in the interstellar medium. Despite this, molecules such as cyanamide, NH2CN, are largely underpredicted by current astrochemical models suggesting that the network of reactions currently used to describe this species and its tautomer carbodiimide, HNCNH, are incomplete. Here, we performed a theoretical investigation of the reaction of ground state atomic carbon C(3P) with molecular nitrogen N2 in both the gas-phase and on the surface of amorphous solid water (ASW) clusters to examine its potential importance in the formation of NH2CN and HNCNH. We show that the reaction of gas-phase C-atoms with N2 molecules already present on the ASW surface results in the barrierless formation of CNN. Following exothermic hydrogenation reactions, the N-N bond of the C-N-N bearing intermediates is broken allowing the formation of molecules with N-C-N backbones through cyclic intermediates over low barriers. To test the importance of these processes to NH2CN and HNCNH formation, these reactions were included in a three-phase astrochemical model of low-mass protostellar evolution employing a reaction network that was updated to better describe the formation and destruction pathways of related small nitrogen bearing molecules. These simulations demonstrate that the ice surface reaction between C and N2 represents by far the dominant source of NH2CN and HNCNH in protostellar environments and in dense clouds.

In this paper, study sums $A=\{a,b\}_2+\{c,d\}_2$ of two symbols in $K_2(F)/2K_2(F)$ when $\operatorname{char}(F)=2$. We first prove a chain lemma that connects $A$ to $B=\{α,β\}_2+\{γ,δ\}_2$ by a finite sequence of small steps when $A \equiv B$. We use this lemma to prove that $\{a,b,c,d\}_2 \in K_4(F)/2K_4(F)$ is a well-defined invariant of $A$, and that this invariant is trivial if and only if $A$ is congruent to a single symbol in $K_2(F)/4K_2(F)$. We also bound the symbol length of $C$ in $K_2(F)/2^m K_2(F)$ from above when $C$ is the sum of up to four symbols in $K_2(F)/2^{m+1}K_2(F)$.

The quantified Boolean formula problem (QBF) is a well-known PSpace-complete problem with rich expressive power, and is generally viewed as the SAT analogue for PSpace. Given that many problems today are solved in practice by reducing to SAT, and then using highly optimized SAT solvers, it is natural to ask whether problems in PSpace are amenable to this approach. While SAT solvers exploit hidden structural properties, such as backdoors to tractability, backdoor analysis for QBF is comparatively very limited. We present a comprehensive study of the (parameterized) complexity of QBF parameterized by backdoor size to the largest tractable syntactic classes: HORN, 2-SAT, and AFFINE. While SAT is in FPT under this parameterization, we prove that QBF remains PSpace-hard even on formulas with backdoors of constant size. Parameterizing additionally by the quantifier depth, we design FPT-algorithms for the classes 2-SAT and AFFINE, and show that 3-HORN is W[1]-hard. As our next contribution, we vastly extend the applicability of QBF backdoors not only for the syntactic classes defined above but also for tractable classes defined via structural restrictions, such as formulas with bounded incidence treewidth and quantifier depth. To this end, we introduce enhanced backdoors: these are separators S of size at most k in the primal graph such that S together with all variables contained in any purely universal component of the primal graph minus S is a backdoor. We design FPT-algorithms with respect to k for both evaluation and detection of enhanced backdoors to all tractable classes of QBF listed above and more.

We study a boost-invariant, out-of-equilibrium fluid of non-interacting Dirac fermions with a finite canonical spin potential. After solving the Dirac equation in Milne coordinates, we exactly diagonalize the non-equilibrium density operator and compute the partition function and expectation values of relevant observables, including spin polarization, energy density, longitudinal and transverse pressures, spin density, and \emph{spin torque}, i.e. the source of spin non-conservation. We find an analytic expression for the partition function at finite spin potential, and show numerically that thermodynamic relations connecting it to thermodynamic functions hold in the system under consideration. We show that, in a boost-invariant system, both shear-induced polarization and the spin Hall effect are absent, and that a non-vanishing polarization can only arise from a finite spin potential in a free theory. We obtain an analytic expression for the spin polarization as a function of the spin potential in some particular cases, and otherwise compute numerically its exact expectation value at finite spin potential. Our results are discussed in the context of relativistic spin hydrodynamics and quark--gluon plasma phenomenology.

Data-based adaptive optimization methods hold great promise for the performance optimization of uncertain, time-varying processes. However, current methods are often based on continuous perturbation which is in general undesired for real-life (e.g., industrial) applications. In this paper, a new uncertainty-based perturb-and-observe method is developed that addresses this limitation and reduces the required number of perturbations, while retaining the capability to track time-varying optima. The method is based on the philosophy of `only perturbing when needed,' and is shown to converge to the optimum under mild conditions. A simulation-based case study on a photo-voltaic solar array demonstrates that it can outperform the standard perturb and observe approach as well as three other data-based optimization methods.

An extension of the multi-level hp Finite Cell Method is proposed for the simulation of thermoviscoplastic problems with temperature-dependent material behavior. The approach combines hierarchical adaptive refinement with a non-negative moment fitting (NNMF) quadrature scheme for efficient and robust integration of non-linear, history-dependent constitutive models on cut cells. The NNMF formulation yields sparse, positive quadrature rules that significantly reduce the number of integration points while maintaining stability and accuracy. An error-indicator-driven hp-refinement strategy enables localized resolution of strain and thermal gradients during the non-linear solution process. The framework is implemented within a partitioned thermo-mechanical scheme and evaluated on benchmark and application-oriented examples. The results demonstrate improved accuracy and substantial computational savings compared to standard integration approaches.

We present two general methods to implement quantum circuits for the direct measuring of local unitary invariants on quantum computers. We work these out for important three-qubit invariants, and also demonstrate these on the IBM Quantum Platform for important entanglement measures of three qubits.

How difficult can it be to implement a PID controller? The answer is twofold. Implementing the PID control law is simple and computationally inexpensive. However, this basic form will not work in practical applications. The primary reason for this is the various physical limitations of the actuator. Measurement noise, different implementations depending on the various structures (P, PI, PD or PID), bumpless transfer, and varying sampling time also result in problems rendering the basic form inoperable. PID implementation is therefore more difficult than meets the eye. This paper introduces a reference implementation of the PID controller which considers these practical issues. It includes pseudo-code, discussion of the implementation choices and simulation of carefully selected, important test cases.

With the ever-increasing usage of serverless computing in both industry and academia, it is essential to understand the mechanisms that power the underlying platforms. As serverless is more than ten years old, there are different platforms with vastly different approaches. We show that, next to the traditional and popular platforms, a second generation of serverless platform has emerged. While first-generation platforms are based on containerized, centralized execution, the new generation leverages lightweight isolates and edge deployment. This evolution reduces warm request latency from approximately 40 ms to around 10 ms and reduces cold starts to an afterthought, but limits the execution environment. In this paper, we gather and analyze all publicly available information to provide detailed insights into the underlying architecture of seven platforms and then run a microbenchmark-based evaluation totaling more than 38 million function calls to gain a deeper understanding their performance.