arXiv subjects

Raul Jimenez

Publications and source records attributed to Raul Jimenez.

At least 19 recordsLinked to original sources

arXiv2026

Reaching the Metallicity Floor at $z\sim 10$: Lensed Star Clusters at Cosmic Dawn and Cosmic Noon

Origins of globular clusters (GCs) are linked to the assembly of their host galaxies. We analyze star-cluster populations in two strongly lensed systems that bracket Cosmic Dawn and Cosmic Noon: the Cosmic Gems arc (GEMS) at z=9.625, among the first galaxies, and the Sparkler at z=1.378. New STARRED deconvolution photometry of GEMS provides SEDs for ten unique, doubly imaged cluster candidates, while a homogeneous Bayesian analysis places both populations on a common cosmological timeline. The GEMS clusters formed at $z_{\rm form}\approx 10$--$11$ (median $\simeq10.2$), consistent with halo assembly at or above the atomic-cooling scale. Their photometry requires low metallicities: individual clusters are consistent with $[Z/{\rm H}] \lesssim -1.2$, and the data exclude $[Z/{\rm H}]\geq-0.5$, though they cannot distinguish reliably below $[Z/{\rm H}] \simeq -1.5$. This conclusion is unchanged when using stellar-population models including binary evolution---important for ultraviolet emission at this age---yielding similarly low metallicities, $[Z/{\rm H}]=-2.2$ to $-2.7$. The formal estimate, $[Z/{\rm H}] = -2.3\pm0.3$, is consistent with the Milky Way GC metallicity floor, though its value remains prior-dependent. The Sparkler clusters formed $\sim2.5$ Gyr later, at $z_{\rm form}\approx 2$--$3.5$ in a Cosmic Noon dwarf galaxy, and are more enriched ($[Z/{\rm H}] \approx -0.5$). Comparison with Milky Way GCs places GEMS in an exceptionally early, metal-poor regime and the Sparkler among later, more enriched populations, though neither association uniquely determines an in-situ or ex-situ origin. Closed-box and gas-regulator calculations show both systems are compatible with limited pre-enrichment followed by rapid enrichment and accretion-regulated growth. Together, they probe distinct cluster-forming environments from Cosmic Dawn to Cosmic Noon.

astro-ph.GA↗

arXiv2026

Cosmic CORALS: Timing the Universe with high-z star clusters

In this work, we explore the potential of anchoring the age-redshift relation across cosmic time by probing the oldest star clusters at high redshift, now observed thanks to the James Webb Space Telescope in strongly lensed fields. As a case study, we consider one of the highest-redshift systems observed, the Cosmic Gems arc at $z=9.625$. We perform image deconvolution of multi-band JWST imaging, identifying a total of 20 point sources along the arc. We derive the stellar ages through a cosmology-independent spectral energy distribution (SED) fitting framework, ensuring that these measurements can be used as unbiased cosmological anchors. By combining these high-z systems with state-of-the-art local globular cluster ages, we perform a joint Bayesian fit to the age-redshift relation in a flat $\Lambda$CDM model, measuring $H_0=70^{+27}_{-16}\ \rm{km\ s^{-1}\ Mpc^{-1}}$ and $\Omega_m=0.33^{+0.37}_{-0.21}$. While these constraints are still loose, we show that the slope of the degeneracy, a power-law in the $\Omega_m - H_0$ plane, is highly dependent on the redshift of the sources, becoming shallower as redshift increases. Leveraging this geometric rotation, we present forecasts showing that a future sample of $\sim 300$ lensed proto-globular clusters well-distributed up to $z \approx 10$ could tighten the statistical precision to $4\%$ on $H_0$ and $11\%$ on $\Omega_m$, competitive with and independent of methods currently in use. The present work, therefore, represents a new avenue in cosmology and comes at a timely moment, when JWST observes high-redshift lensed star clusters routinely, Euclid and the Nancy Grace Roman Space Telescope uncover new strong lensing fields, and close to the start of operation of the ESO Extremely Large Telescope.

astro-ph.CO↗

arXiv2026

Physics-Informed Neural Embeddings of PDE Solution Families

We introduce a physics-informed framework for learning finite-dimensional embeddings of solution families of partial differential equations. The method uses a multihead Physics-Informed Neural Network in which a shared body learns a latent manifold representing the solution space, while linear heads reconstruct individual solutions associated with different initial conditions. A head-orthogonalization penalty removes degeneracies in the latent representation and stabilizes the principal-component spectrum across training realizations. Because the initial condition is built into the network output by construction, these principal components measure the additional variability the network learns on top of the initial profile, not the full solution itself. We apply the method to the one-dimensional viscous Burgers equation, with the heat and wave equations as robustness checks. For a latent dimension $n_b=20$, the learned manifolds exhibit pronounced effective dimensional reduction: for Burgers dynamics, only $2$-$4$ principal components capture about $95\%$ of the latent-space variance, while $4$-$7$ capture about $99\%$, depending on the initial-condition family; the same qualitative compression holds for the heat and wave equations. We also split the wavenumber axis into bands (``Fourier shells'') and measure how much each band contributes to every principal component. The resulting frequency profile is invariant under the change-of-basis freedom that the orthogonalization penalty leaves in the latent space, and is therefore reproducible across independent training runs. More broadly, this establishes the learned spectral profiles and principal components as robust observables of solution-manifold geometry.

cs.LG↗

arXiv2026

Gravitational Duals from Equations of State II: Large Hierarchies and False Vacua

We investigate the reconstruction of holographic duals for strongly coupled quantum field theories in regimes characterized by large hierarchies and the presence of false vacua. Within the gauge/gravity duality, these features translate into non-trivial thermodynamic behaviour and exotic renormalization group flows, including skipping flows between non-adjacent fixed points. Building on previous work based on Physics-Informed Neural Networks (PINNs), we extend the holographic inverse problem of reconstructing the bulk scalar potential from boundary thermodynamic data into this new regime. This setting presents a variety of conceptual and numerical challenges, such as near-degenerate states, large hierarchies of energy scales, and regions of the potential that are not directly probed by the input data. We develop a set of methodological advances that overcome these obstacles, thereby improving the established PINNs-based methodology and extending it to new physical regimes of interest that were previously out of reach. Applying the developed framework, we demonstrate accurate reconstruction of scalar potentials deep into the false vacuum regime, achieving robust agreement with the physical features of the underlying thermodynamics despite significant numerical stiffness. Our results extend the bridge between holography and machine learning, and suggest that data-driven approaches can provide new insights into the structure of strongly coupled systems.

hep-th↗

arXiv2026

Recovering Sharp Conductivity Features in the Finite-Data Calder\'on Problem with Physics-Informed Neural Networks

Physics-informed neural networks (PINNs) have recently emerged as a promising framework for addressing the Calder\'on inverse problem from limited boundary data. In this work, we revisit neural Calder\'on inversion by introducing multiscale boundary excitations based on randomized wavelet functions and investigating the role of Fourier-feature encoding (FFE) for representing sharp conductivity variations. We propose a physics-informed reconstruction framework that represents the unknown conductivity and the associated family of electric potentials with separate neural networks conditioned on the applied boundary excitations. The governing elliptic PDE is enforced through physics-informed residuals, while finite Dirichlet-to-Neumann (DtN) data are incorporated through boundary losses. Using synthetic data from a finite-difference forward solver, we evaluate the method on conductivity fields with inclusions, sharp interfaces, smooth profiles, and heterogeneous media. Results show that the framework recovers dominant conductivity structures from finite boundary measurements with relative errors between $3\%-12\%$ approximately. We show that FFE improves the reconstruction of localized sharp features, particularly for inclusions and interfaces, but are not universally optimal, with raw-coordinate networks performing competitively for smoother fields. These results highlight coordinate representations and boundary excitation design as key factors in neural Calder\'on inversion.

cs.LG↗

arXiv2026

AI Scientists as Engines of Discovery: A Case for Development within Reformed Institutions

Agentic artificial intelligence (AI) systems are beginning to assist, accelerate, and partially automate scientific discovery, performing tasks that span literature synthesis, code generation, data analysis, hypothesis proposal, and model criticism. We argue that this transition is qualitative rather than incremental, and that suitably designed multi-agent systems may evolve from passive computational tools into ``AI scientists'' that can expand the hypothesis-generating and verification capacity of science. Such systems must be developed and deployed within a scientific ecosystem fit for purpose: institutions must be redesigned for verification, accountability, interpretability, and dual-use safety. We sketch how multi-agent architectures, illustrated by the prototype framework \textit{Denario}, accelerate the discovery cycle and traverse model spaces beyond human reach; examine what this implies for authorship, peer review, and the enduring role of human scientists; and close with recommendations for governing AI as an epistemic actor rather than a mere instrument.

cs.AI↗

arXiv2026

From Evidence to Evident: Decisive Cosmological Evidence for the Normal Neutrino Mass Hierarchy

Cosmological data have reached the precision needed to turn the neutrino mass ordering from a weak Bayesian preference into a decisive model-selection test. We compute the evidence for the Normal and Inverted Hierarchies by combining DESI DR2 clustering with NuFIT oscillation data. In baseline $\Lambda$CDM, DESI DR2 plus Planck CamSpec gives $\Sigma m_\nu<0.0642\,{\rm eV}$ at 95\% confidence, close to the normal-ordering floor, $\Sigma m_\nu^{\rm NH}\simeq0.059\,{\rm eV}$, but well below the inverted-ordering minimum, $\Sigma m_\nu^{\rm IH}\simeq0.099\,{\rm eV}$. Thus the inverted hierarchy lies in the tail of the cosmological likelihood. The Bayes factor $K=P(D|{\rm NH})/P(D|{\rm IH})$ exceeds $460$ even for a conservative reference prior, and remains strong, $K>40$, in baseline-model extensions. We show that this result is robust to the choice between a reference prior and a physically motivated logarithmic hierarchical prior, marking the transition from {\em prior-sensitive evidence} to {\em likelihood-dominated exclusion} of the inverted hierarchy within standard cosmology. Embedding these priors in the two-dimensional design space of measure (logarithmic versus linear in mass) and structure (hierarchical versus non-hierarchical), we find that all four prior constructions give decisive evidence under DESI DR2, with residual prior dependence governed mainly by the measure -- a factor $\sim\!10$ in $K$ -- rather than by the hierarchy assumption. At the prior-family level, the evidence favors the SJPV prior predictive over HS by a Bayes factor above $4,700$ across each matched-support variation tested. The favored normal ordering pushes the effective Majorana mass to the few-meV regime, with median $m_{\beta\beta}=3.28\,{\rm meV}$ and 95\% credible interval $0.95<m_{\beta\beta}<11.55\,{\rm meV}$, below the inverted-ordering target for upcoming neutrinoless double-beta decay experiments.

astro-ph.CO↗

arXiv2026

The Coherence Principle: A Falsifiable Prior for Model Selection from the Grammar of Theories

Bayesian model selection in cosmology and particle physics is often performed where posterior odds inherit a strong, often unacknowledged dependence on the prior assigned to competing models. Standard responses -- reference priors, hierarchical priors, or appeals to naturalness -- ignore relevant theoretical knowledge or rely on criteria hard to define operationally. We propose the \emph{Coherence Principle}: a reproducible prescription for assigning model priors according to compatibility with the validated structure of an existing theory. This structure, or \emph{grammar}, includes symmetries, conservation laws, locality, Lorentz invariance, and universality patterns. Unmotivated violations of these rules incur a coherence cost, converted into a prior weight through a maximum-entropy exponential form controlled by one calibratable parameter $\alpha$. The resulting prior is distinct from both the Bayesian Occam factor and naturalness: it penalizes not parameter volume or fine tuning, but departures from validated theoretical grammar. We illustrate the principle with examples from cosmology and fundamental physics: neutrino mass mechanisms, dark energy and modified gravity, inflation, beyond-Standard-Model sectors, and hierarchical astrophysical inference. We test it also on four historical cases -- general relativity, Pauli's neutrino, parity violation, and special relativity -- where evidential and theoretical contexts can be reconstructed. These examples show that it favors the historically successful choice when the proper grammar is defined in the correct domain and time. The Coherence Principle makes explicit a common but usually tacit part of physical reasoning: trust in validated structural rules. It turns this judgment into a transparent, testable, and overrulable component of Bayesian inference, leaving empirical likelihoods free to dominate when data are sufficiently constraining.

astro-ph.CO↗

arXiv2026

AI--Assisted Exploration: DHOST Theories without Quantum Ghosts

We ask whether a local symmetry can organize both classical degeneracy and perturbative stability in DHOST theories. An AI-assisted search finds a candidate in a constant-disformal image of Einstein gravity. We identify it as a field-dependent diffeomorphism plus a vertical translation of a spectator scalar and extend it to every regular first-derivative map $\widetilde g_{\mu\nu}=C(\phi,X)g_{\mu\nu}-D(\phi,X)\nabla_\mu\phi\nabla_\nu\phi$, which pulls the spectator translation back to an exact local gauge redundancy. We derive its closed generator and show that $\mathcal J=C-XC_X+X^2D_X$ controls kinetic invertibility, the generator denominator and the metric-map determinant. This regular ($\mathcal J\neq0$) construction is distinct from non-invertible mimetic symmetry. We prove that a same-field sector $K(\phi,\widetilde X)$ preserves the local shift exactly when its scalar density is variationally trivial. For one scalar on a generic branch this requires constant $K$; nonconstant $K(\widetilde X)$ leaves only a global shift. The multi-field extension has local group $\mathbb R^n$ and admits determinant-type topological exceptions for $n\geq d$. Under standard local BV hypotheses, the spectator, its ghost and their antifields form a contractible quartet, so the spectator fibre adds no independent local counterterm, gauge deformation or anomaly class. The constant-map Einstein image is a special two-mode quartic-Horndeski subclass, while regular nonconstant $K$ restores one scalar. Finally, the complete canonical Einstein--scalar one-loop divergence shows that $(\widetilde\Box\phi)^2$ is equation-of-motion redundant at first loop order. The essential $\widetilde X^2$ pole pulls back to a first-derivative counterterm throughout the regular orbit and introduces no additional perturbative mode at $O(\hbar)$ within the stated hyperbolic EFT domain.

astro-ph.CO↗

arXiv2026

A Bell Experiment in an Entangled Universe

We propose a possible quantum signature of the early Universe that could lead to observational imprints of the quantum nature of the inflationary period. Graviton production from the presence of a classical, coherent state of the inflaton scalar field results in entangled states in the gravitons' polarizations. At horizon crossing, interactions between the gravitons and (lower scale) inflatons, together with the gathering of ``which-path information'' from the cosmological horizon, perform the required Bell experiments leading to a definitive measure, which can be imprinted in the scalar correlation four-point function. This is because of a non-trivial effect due to the derivatives on two scalar fluctuations, and it provides a fingerprint that depends on the polarization of the graviton that Alice and/or Bob measured in their patch. We hint how this signature could be measured in the high-order correlation function of galaxies, in particular on the halo bias and the intrinsic alignment.

astro-ph.CO↗

arXiv2026

A Bell experiment during inflation: probing quantum entanglement in tensor fluctuations through correlations of primordial scalar curvature perturbations

We propose a method that provides an observational signature of the quantum origin of primordial fluctuations generated during inflation. The method gives a prescription for testing a Bell inequality constructed exclusively from the standard scalar and tensor perturbations of minimal single-field inflation. We consider an inflationary spacetime populated by pairs of gravitons entangled in their polarization states. Third-order interactions between two scalars and one graviton transfer polarization information to the scalar sector through the product of spatial derivatives of scalars with the tensor polarization factors. Rather than performing the full multidimensional momentum integrations, we isolate and compute the tensor polarization structure of the primordial scalar eight-point correlation function. This eight-point correlation function factorizes into the product of four scalar two-point functions associated with opposite (mirrored) momentum configurations in Fourier space. This factorization falls from the fact that the two gravitons are spatially well-separated within the cosmological horizon of inflation, replicating the setup of standard Bell experiments. Through these interactions, we track how non-local correlations between both gravitons from polarization entanglement are imprinted on the scalar sector. We show that, for specific configurations of the scalar momenta after the end of inflation (detailed in the text), this observable can be used to construct a Bell-violating quantity in a way that matches the well-known Clauser-Horne-Shimony-Holt inequality definition. In principle, this offers a route to probe the quantum nature of primordial fluctuations through observables accessible today.

astro-ph.CO↗

arXiv2026

Inflation without an Inflaton III: non-Gaussian signatures

We investigate primordial non-Gaussianity in the Inflation without an Inflaton (IWI) framework, where scalar perturbations are generated at second order by primordial gravitational waves in Einstein gravity on an exact de Sitter (dS) background. Since scalar modes are produced nonlinearly from tensor modes, non-Gaussianity is an intrinsic prediction of the mechanism. We compute the corresponding scalar bispectrum, derive the relevant contribution to the three-point function of the scalar potential, and evaluate its shape numerically. We find that, unlike the scalar power spectrum, the bispectrum depends logarithmically on the ultraviolet cutoff set by the end of inflation, indicating a structural difference between the two- and three-point statistics in this scenario. Its shape is enhanced toward squeezed configurations, but its amplitude becomes strongly suppressed once the scalar power spectrum is normalized to the observed value. The resulting non-Gaussianity at CMB scales is therefore negligibly small, well below present observational sensitivity.

astro-ph.CO↗

arXiv2026

Chemo-dynamical reconstruction of Milky Way globular cluster progenitors: Age-metallicity relations and the universality of multiple stellar populations

Globular clusters encode the hierarchical assembly history of the Milky Way and the physics of multiple stellar populations. Using homogeneous stellar parameters for 69 Galactic globular clusters derived while modelling multiple populations, we reconstruct progenitor-specific age--metallicity relations (AMRs) and test whether helium-related multiple-population (MP) properties depend on progenitor origin once cluster mass and metallicity are controlled for. Ages, helium spreads ($\delta Y$), mean helium abundances ($\bar{Y}$), and first-population fractions ($f_{\rm P1}$) are drawn from hierarchical Bayesian CMD modelling. Progenitor families are identified via chemo-dynamical clustering, AMRs reconstructed within a hierarchical Bayesian framework, and MP indicators tested for environmental dependence. Enrichment timescales are consistent with $\tau \lesssim 2$\,Gyr, though individual progenitors prefer shorter values when fitted independently. The primary distinction is the extent of chemical evolution: most systems reach $\Delta[\mathrm{Fe/H}] \sim 1.1$--$1.3$\,dex while Sagittarius achieves ${\sim}1.6$\,dex and higher terminal metallicities. Gaia--Sausage--Enceladus and low-energy/Kraken are the dominant accretion events. Neither $\delta Y$ nor $\bar{Y}$ depends on progenitor origin; the mass--MP scaling is indistinguishable across in-situ and accreted systems. Sequoia clusters alone show higher $f_{\rm P1}$ at fixed mass and metallicity. AMRs carry fossil signatures of progenitor chemical evolution and mass hierarchy. Helium enrichment amplitude is regulated by cluster mass and blind to environment, pointing to universal cluster-scale formation physics, with the sole exception of a residual dependence in $f_{\rm P1}$, suggesting the enriched-star fraction retains a secondary environmental imprint.

astro-ph.GA↗

arXiv2026

Learning embeddings of non-linear PDEs: the Burgers' equation

Embeddings provide low-dimensional representations that organize complex function spaces and support generalization. They provide a geometric representation that supports efficient retrieval, comparison, and generalization. In this work we generalize the concept to Physics Informed Neural Networks. We present a method to construct solution embedding spaces of nonlinear partial differential equations using a multi-head setup, and extract non-degenerate information from them using principal component analysis (PCA). We test this method by applying it to viscous Burgers' equation, which is solved simultaneously for a family of initial conditions and values of the viscosity. A shared network body learns a latent embedding of the solution space, while linear heads map this embedding to individual realizations. By enforcing orthogonality constraints on the heads, we obtain a principal-component decomposition of the latent space that is robust to training degeneracies and admits a direct physical interpretation. The obtained components for Burgers' equation exhibit rapid saturation, indicating that a small number of latent modes captures the dominant features of the dynamics.

math.AP↗

arXiv2026

The Age of the Universe with Globular Clusters IV: Multiple Stellar Populations

We revisit the determination of the age of the Universe from galactic globular clusters, extending previous analyses by explicitly accounting for the presence of multiple stellar populations within each cluster. Using high--quality \textit{Hubble Space Telescope} color--magnitude diagrams for 69 globular clusters, we relax the standard single--population assumption, and model two stellar populations with independent ages, metallicities, helium abundances, and population fractions. The inference is performed using the full color--magnitude diagram morphology, an explicit treatment of field contamination, and a hierarchical framework that propagates non--Gaussian age posteriors. Allowing for multiple stellar populations has a negligible impact on globular cluster age estimates. The ages of the oldest populations remain fully consistent with those obtained under the single--population assumption, with differences at the $0.6\sigma$ level. Restricting to the metal--poor subsample ([Fe/H] $< -1.5$), we infer a dominant old component with mean age $t_{\rm GC}=13.61\pm0.25\,\mathrm{(stat)}\,\pm0.23 \mathrm{(sys)}\,\mathrm{Gyr}$. Adopting a conservative delay between the Big Bang and the formation of the first globular clusters, we obtain an age of the Universe of $t_{\rm U}=13.81\pm0.25\,\mathrm{(stat)}\,\pm0.23 \mathrm{(sys)}\,\mathrm{Gyr}$. In addition to age constraints, our analysis yields simultaneous measurements of metallicity and helium content for the different populations, including constraints on helium enrichment and population fractions which are consistent with independent determinations from the literature. These results demonstrate that globular--cluster--based cosmic chronometry is robust to stellar population complexity, reinforcing its role as a precise and largely cosmological model--independent probe of the age of the Universe.

astro-ph.GA↗

arXiv2026

The Atacama Cosmology Telescope: Constraints on Local Non-Gaussianity from the ACT Cluster Catalog

We derive constraints on local-type primordial non-Gaussianity using the ACT DR6 Sunyaev--Zel'dovich cluster catalog. Modeling the redshift- and mass-dependent number counts of 1,201 clusters in the 10,347~deg$^2$ Legacy region, and accounting for survey completeness, intrinsic SZ scatter, and a weak-lensing-calibrated mass bias, we compute theoretical abundances using the Log--Edgeworth halo mass function. Assuming $\Lambda$CDM with well-motivated external priors, we obtain $f_{\rm NL} = 55 \pm 125$ (68% CL), consistent with Gaussian initial conditions. These constraints probe comoving scales of $5$--$10~{\rm Mpc}~h^{-1}$, complementing CMB bispectrum and scale-dependent bias measurements, which do not reach such small scales. We also find evidence for a 16.4% residual mass bias, which, although heavily informed by our adopted priors, plays a key role in matching observed and predicted counts but has negligible effect on $f_{\rm NL}$ constraints. We briefly discuss robustness of the results under relaxed priors and the prospects for next-generation SZ and lensing surveys to strengthen cluster-based tests of primordial non-Gaussianity.

astro-ph.CO↗

arXiv2025

Inflation without an Inflaton II: observational predictions

We present a complete computation of the scalar power spectrum in the \emph{inflation without inflaton} (IWI) framework, where the inflationary expansion is driven solely by a de~Sitter (dS) background and scalar fluctuations arise as second-order effects sourced by tensor perturbations. By explicitly deriving and numerically integrating the full second-order kernel of the Einstein equations, we obtain a scale-invariant scalar spectrum without invoking a fundamental scalar field. In this framework, the amplitude of the scalar fluctuations is directly linked to the scale of inflation. More precisely, we show that matching the observed level of scalar fluctuations, $\Delta_{\phi}^2(k_\ast)\approx 10^{-9}$ at Cosmic Microwave Background (CMB) scales, fixes the inflationary energy scale $H_{\rm inf}$ as a function of the number of observed e-folds $N_{\rm obs}$. For $N_{\rm obs}\simeq 30 - 60$, we find $H_{\rm inf} \simeq 5\times 10^{13}\,\mathrm{GeV} - 2\times 10^{10}\,\mathrm{GeV}$, corresponding to a tensor-to-scalar ratio $r \simeq 0.01 - 5\times 10^{-9}$. In particular, requiring consistency with instantaneous reheating, we predict a number of e-folds of order~$\mathcal{O}(50)$ and an inflationary scale $H_{\rm inf} \simeq 10^{11}\,\mathrm{GeV}$. We also incorporate in our framework the quantum break-time of the dS state and show that it imposes an upper bound on the number of particle species. Specifically, using laboratory constraints on the number of species limits the duration of inflation to $N_{\rm obs}\lesssim 126$ e-folds. These results establish the IWI scenario as a predictive and falsifiable alternative to standard inflaton-driven models, linking the observed amplitude of primordial fluctuations directly to the quantum nature and finite lifetime of dS space.

astro-ph.CO↗

arXiv2025

The Denario project: Deep knowledge AI agents for scientific discovery

We present Denario, an AI multi-agent system designed to serve as a scientific research assistant. Denario can perform many different tasks, such as generating ideas, checking the literature, developing research plans, writing and executing code, making plots, and drafting and reviewing a scientific paper. The system has a modular architecture, allowing it to handle specific tasks, such as generating an idea, or carrying out end-to-end scientific analysis using Cmbagent as a deep-research backend. In this work, we describe in detail Denario and its modules, and illustrate its capabilities by presenting multiple AI-generated papers generated by it in many different scientific disciplines such as astrophysics, biology, biophysics, biomedical informatics, chemistry, material science, mathematical physics, medicine, neuroscience and planetary science. Denario also excels at combining ideas from different disciplines, and we illustrate this by showing a paper that applies methods from quantum physics and machine learning to astrophysical data. We report the evaluations performed on these papers by domain experts, who provided both numerical scores and review-like feedback. We then highlight the strengths, weaknesses, and limitations of the current system. Finally, we discuss the ethical implications of AI-driven research and reflect on how such technology relates to the philosophy of science. We publicly release the code at https://github.com/AstroPilot-AI/Denario. A Denario demo can also be run directly on the web at https://huggingface.co/spaces/astropilot-ai/Denario, and the full app will be deployed on the cloud.

cs.AI↗