Search

There have long been questions about the limits to the validity of relativistic fluid dynamics, and whether it is being used outside its regime of validity in modern simulations of relativistic heavy-ion collisions. An important new tool for answering this question is a causality analysis in the nonlinear regime -- if the solutions of the evolution equations do not respect relativistic causality, they are not a faithful representation of the underlying relativistic theory (in this case, quantum chromodynamics). Using this non-linear criterion, it has recently been shown that hydrodynamics is indeed being used outside its regime of validity in simulations, at least sometimes. Here we explore the phenomenological implications, particularly the quantitative effects of demanding limits on acausality in modern Bayesian parameter estimation. We find that, while typically only a small fraction of the system's energy is initially in an acausal regime, placing strict limits on the allowed energy fraction significantly changes the preferred properties of the initial condition, which in turn alters the extracted medium properties such as bulk viscosity, where large values are no longer favored. These findings highlight the importance of developing better theoretical descriptions of the early-time, out-of-equilibrium dynamics of relativistic heavy-ion collisions., Comment: 13 pages, 9 figures

The JETSCAPE Collaboration reports a new determination of the jet transport parameter $\hat{q}$ in the Quark-Gluon Plasma (QGP) using Bayesian Inference, incorporating all available inclusive hadron and jet yield suppression data measured in heavy-ion collisions at RHIC and the LHC. This multi-observable analysis extends the previously published JETSCAPE Bayesian Inference determination of $\hat{q}$, which was based solely on a selection of inclusive hadron suppression data. JETSCAPE is a modular framework incorporating detailed dynamical models of QGP formation and evolution, and jet propagation and interaction in the QGP. Virtuality-dependent partonic energy loss in the QGP is modeled as a thermalized weakly-coupled plasma, with parameters determined from Bayesian calibration using soft-sector observables. This Bayesian calibration of $\hat{q}$ utilizes Active Learning, a machine--learning approach, for efficient exploitation of computing resources. The experimental data included in this analysis span a broad range in collision energy and centrality, and in transverse momentum. In order to explore the systematic dependence of the extracted parameter posterior distributions, several different calibrations are reported, based on combined jet and hadron data; on jet or hadron data separately; and on restricted kinematic or centrality ranges of the jet and hadron data. Tension is observed in comparison of these variations, providing new insights into the physics of jet transport in the QGP and its theoretical formulation., Comment: 20 pages, 10 figures, 2 tables, submitted to PRC; updated acknowledgements

Large language models (LLMs) can be used to analyze cyber threat intelligence (CTI) data from cybercrime forums, which contain extensive information and key discussions about emerging cyber threats. However, to date, the level of accuracy and efficiency of LLMs for such critical tasks has yet to be thoroughly evaluated. Hence, this study assesses the performance of an LLM system built on the OpenAI GPT-3.5-turbo model [8] to extract CTI information. To do so, a random sample of more than 700 daily conversations from three cybercrime forums - XSS, Exploit_in, and RAMP - was extracted, and the LLM system was instructed to summarize the conversations and predict 10 key CTI variables, such as whether a large organization and/or a critical infrastructure is being targeted, with only simple human-language instructions. Then, two coders reviewed each conversation and evaluated whether the information extracted by the LLM was accurate. The LLM system performed well, with an average accuracy score of 96.23%, an average precision of 90% and an average recall of 88.2%. Various ways to enhance the model were uncovered, such as the need to help the LLM distinguish between stories and past events, as well as being careful with verb tenses in prompts. Nevertheless, the results of this study highlight the relevance of using LLMs for cyber threat intelligence.

A new framework, called x-scape, for the combined study of both hard and soft transverse momentum sectors in high energy proton-proton ($p$-$p$) and proton-nucleus ($p$-$A$) collisions is set up. A dynamical initial state is set up using the 3d-Glauber model with transverse locations of hotspots within each incoming nucleon. A hard scattering that emanates from two colliding hotspots is carried out using the Pythia generator. Initial state radiation from the incoming hard partons is carried out in a new module called I-matter, which includes the longitudinal location of initial splits. The energy-momentum of both the initial hard partons and their associated beam remnants is removed from the hot spots, depleting the energy-momentum available for the formation of the bulk medium. Outgoing showers are simulated using the matter generator, and results are presented for both cases, allowing for and not allowing for energy loss. First comparisons between this hard-soft model and single inclusive hadron and jet data from $p$-$p$ and minimum bias $p$-$Pb$ collisions are presented. Single hadron spectra in $p$-$p$ are used to carry out a limited (in number of parameters) Bayesian calibration of the model. Fair comparisons with data are indicative of the utility of this new framework. Theoretical studies of the correlation between jet $p_T$ and event activity at mid and forward rapidity are carried out., Comment: 18 pages, 15 figures

Information extraction from handwritten documents involves traditionally three distinct steps: Document Layout Analysis, Handwritten Text Recognition, and Named Entity Recognition. Recent approaches have attempted to integrate these steps into a single process using fully end-to-end architectures. Despite this, these integrated approaches have not yet matched the performance of language models, when applied to information extraction in plain text. In this paper, we introduce DANIEL (Document Attention Network for Information Extraction and Labelling), a fully end-to-end architecture integrating a language model and designed for comprehensive handwritten document understanding. DANIEL performs layout recognition, handwriting recognition, and named entity recognition on full-page documents. Moreover, it can simultaneously learn across multiple languages, layouts, and tasks. For named entity recognition, the ontology to be applied can be specified via the input prompt. The architecture employs a convolutional encoder capable of processing images of any size without resizing, paired with an autoregressive decoder based on a transformer-based language model. DANIEL achieves competitive results on four datasets, including a new state-of-the-art performance on RIMES 2009 and M-POPP for Handwriting Text Recognition, and IAM NER for Named Entity Recognition. Furthermore, DANIEL is much faster than existing approaches. We provide the source code and the weights of the trained models at \url{https://github.com/Shulk97/daniel}.

An "element-free" probability distribution is what remains of a probability distribution after we forget the elements to which the probabilities were assigned. These objects naturally arise in Bayesian statistics, in situations where elements are used as labels and their specific identity is not important. This paper develops the structural theory of element-free distributions, using multisets and category theory. We give operations for moving between element-free and ordinary distributions, and we show that these operations commute with multinomial sampling. We then exploit this theory to prove two representation theorems. These theorems show that element-free distributions provide a natural representation for key random structures in Bayesian nonparametric clustering: exchangeable random partitions, and random distributions parametrized by a base measure., Comment: To appear at LICS 2024

Optical Music Recognition (OMR) has made significant progress since its inception, with various approaches now capable of accurately transcribing music scores into digital formats. Despite these advancements, most so-called \emph{end-to-end} OMR approaches still rely on multi-stage processing pipelines for transcribing full-page score images, which introduces several limitations that hinder the full potential of the field. In this paper, we present the first truly end-to-end approach for page-level OMR. Our system, which combines convolutional layers with autoregressive Transformers, processes an entire music score page and outputs a complete transcription in a music encoding format. This is made possible by both the architecture and the training procedure, which utilizes curriculum learning through incremental synthetic data generation. We evaluate the proposed system using pianoform corpora. This evaluation is conducted first in a controlled scenario with synthetic data, and subsequently against two real-world corpora of varying conditions. Our approach is compared with leading commercial OMR software. The results demonstrate that our system not only successfully transcribes full-page music scores but also outperforms the commercial tool in both zero-shot settings and after fine-tuning with the target domain, representing a significant contribution to the field of OMR.

We introduce a minimal model of ultracentral heavy-ion collisions to study the relation between the speed of sound of the produced plasma and the final particles' energy and multiplicity. We discuss how the particles' multiplicity $N_{\textrm{tot}}$ and average energy $E_{\textrm{tot}}/N_{\textrm{tot}}$ is related to the speed of sound $c_s$ by $c_s^2=d \ln (E_{\textrm{tot}}/N_{\textrm{tot}})/d\ln N_{\textrm{tot}}$ if the fluid is inviscid, its speed of sound is constant and all final particles can be measured. We show that finite rapidity cuts on the particles' multiplicity $N$ and energy $E$ introduce corrections between $c_s^2$ and $d \ln (E/N)/d\ln N$ that depend on the system's lifetime. We study analytically these deviations with the Gubser hydrodynamic solution, finding that, for ultrarelativistic bosons, they scale as the ratio of the freezeout temperature $T_{\mathrm{FO}}$ over the maximum initial temperature of the fluid $T_{0}$; the non-thermodynamic aspect of these corrections is highlighted through their dependence on the system's initial conditions., Comment: 21 pages, 8 figures, v2 -- published version, associated git-hub repository: https://github.com/gabriel-sr151/cylindrical-sym-CF

The EXO-POPP project aims to establish a comprehensive database comprising 300,000 marriage records from Paris and its suburbs, spanning the years 1880 to 1940, which are preserved in over 130,000 scans of double pages. Each marriage record may encompass up to 118 distinct types of information that require extraction from plain text. In this paper, we introduce the M-POPP dataset, a subset of the M-POPP database with annotations for full-page text recognition and information extraction in both handwritten and printed documents, and which is now publicly available. We present a fully end-to-end architecture adapted from the DAN, designed to perform both handwritten text recognition and information extraction directly from page images without the need for explicit segmentation. We showcase the information extraction capabilities of this architecture by achieving a new state of the art for full-page Information Extraction on Esposalles and we use this architecture as a baseline for the M-POPP dataset. We also assess and compare how different encoding strategies for named entities in the text affect the performance of jointly recognizing handwritten text and extracting information, from full pages., Comment: To be published in: International Conference on Document Analysis and Recognition - ICDAR 2024

In this paper we present two design generations of metasurface-based planar microlenses implemented on Front-Side Illumination SPAD pixels. This kind of microlens is an alternative to conventional reflow microlens. It offers more degrees of freedom in term of design, especially the capability to design off-axis microlens to gather light around the SPAD photodiode. The two generations of microlenses have been fabricated on STMicroelectronics SPAD and characterized. We validated the sensitivity improvement offered by extended metasurface-based microlens. We also confirmed the impact of lithography capability on metasurface performances, highlighting the

The BigCode project, an open-scientific collaboration focused on the responsible development of Large Language Models for Code (Code LLMs), introduces StarCoder2. In partnership with Software Heritage (SWH), we build The Stack v2 on top of the digital commons of their source code archive. Alongside the SWH repositories spanning 619 programming languages, we carefully select other high-quality data sources, such as GitHub pull requests, Kaggle notebooks, and code documentation. This results in a training set that is 4x larger than the first StarCoder dataset. We train StarCoder2 models with 3B, 7B, and 15B parameters on 3.3 to 4.3 trillion tokens and thoroughly evaluate them on a comprehensive set of Code LLM benchmarks. We find that our small model, StarCoder2-3B, outperforms other Code LLMs of similar size on most benchmarks, and also outperforms StarCoderBase-15B. Our large model, StarCoder2- 15B, significantly outperforms other models of comparable size. In addition, it matches or outperforms CodeLlama-34B, a model more than twice its size. Although DeepSeekCoder- 33B is the best-performing model at code completion for high-resource languages, we find that StarCoder2-15B outperforms it on math and code reasoning benchmarks, as well as several low-resource languages. We make the model weights available under an OpenRAIL license and ensure full transparency regarding the training data by releasing the SoftWare Heritage persistent IDentifiers (SWHIDs) of the source code data.

State-of-the-art end-to-end Optical Music Recognition (OMR) has, to date, primarily been carried out using monophonic transcription techniques to handle complex score layouts, such as polyphony, often by resorting to simplifications or specific adaptations. Despite their efficacy, these approaches imply challenges related to scalability and limitations. This paper presents the Sheet Music Transformer, the first end-to-end OMR model designed to transcribe complex musical scores without relying solely on monophonic strategies. Our model employs a Transformer-based image-to-sequence framework that predicts score transcriptions in a standard digital music encoding format from input images. Our model has been tested on two polyphonic music datasets and has proven capable of handling these intricate music structures effectively. The experimental outcomes not only indicate the competence of the model, but also show that it is better than the state-of-the-art methods, thus contributing to advancements in end-to-end OMR transcription., Comment: Submitted to the International Conference on Document Analysis and Recognition 2024

Prompt photons are created in the early stages of heavy ion collisions and traverse the QGP medium without any interaction. Therefore, photon-triggered jets can be used to study the jet quenching in the QGP medium. In this work, photon-triggered jets are studied through different jet and jet substructure observables for different collision systems and energies using the JETSCAPE framework. Since the multistage evolution used in the JETSCAPE framework is adequate to describe a wide range of experimental observables simultaneously using the same parameter tune, we use the same parameters tuned for jet and leading hadron studies. The same isolation criteria used in the experimental analysis are used to identify prompt photons for better comparison. For the first time, high-accuracy JETSCAPE results are compared with multi-energy LHC and RHIC measurements to better understand the deviations observed in prior studies. This study highlights the importance of multistage evolution for the simultaneous description of experimental observables through different collision systems and energies using a single parameter tune., Comment: 4 pages, 5 figures. Proceedings of Quark Matter 2023 - XXXth International Conference on Ultra-relativistic Nucleus-Nucleus Collisions, Houston, TX, 3-9 September 2023

The JETSCAPE Collaboration reports the first multi-messenger study of the QGP jet transport parameter $\hat{q}$ using Bayesian inference, incorporating all available hadron and jet inclusive yield and jet substructure data from RHIC and the LHC. The theoretical model utilizes virtuality-dependent in-medium partonic energy loss coupled to a detailed dynamical model of QGP evolution. Tension is observed when constraining $\hat{q}$ for different kinematic cuts of the inclusive hadron data. The addition of substructure data is shown to improve the constraint on $\hat{q}$, without inducing tension with the constraint due to inclusive observables. These studies provide new insight into the mechanisms of jet interactions in matter, and point to next steps in the field for comprehensive understanding of jet quenching as a probe of the QGP., Comment: 4 pages, 2 figures. Proceedings of Quark Matter 2023 - XXXth International Conference on Ultra-relativistic Nucleus-Nucleus Collisions, Houston, TX, 3-9 September 2023

Considerable information about the early-stage dynamics of heavy-ion collisions is encoded in the rapidity dependence of measurements. To leverage the large amount of experimental data, we perform a systematic analysis using three-dimensional hydrodynamic simulations of multiple collision systems -- large and small, symmetric and asymmetric. Specifically, we perform fully 3D multi-stage hydrodynamic simulations initialized by a parameterized model for rapidity-dependent energy deposition, which we calibrate on the hadron multiplicity and anisotropic flow coefficients. We utilize Bayesian inference to constrain properties of the early- and late- time dynamics of the system, and highlight the impact of enforcing global energy conservation in our 3D model.

Premonoidal categories and Freyd categories provide an encompassing framework for the semantics of call-by-value programming languages. Premonoidal categories are a weakening of monoidal categories in which the interchange law for the tensor product may not hold, modelling the fact that effectful programs cannot generally be re-ordered. A Freyd category is a pair of categories with the same objects: a premonoidal category of general programs, and a monoidal category of 'effect-free' programs which do admit re-ordering. Certain recent innovations in semantics, however, have produced models which are not categories but bicategories. Here we develop the theory to capture such examples by introducing premonoidal and Freyd structure in a bicategorical setting. The second dimension introduces new subtleties, so we verify our definitions with several examples and a correspondence theorem (between Freyd bicategories and certain actions of monoidal bicategories) which parallels the categorical framework., Comment: In Proceedings ACT 2023, arXiv:2312.08138

This document serves as an overview of the different mechanisms and areas of governance in the BigCode project. It aims to support transparency by providing relevant information about choices that were made during the project to the broader public, and to serve as an example of intentional governance of an open research project that future endeavors can leverage to shape their own approach. The first section, Project Structure, covers the project organization, its stated goals and values, its internal decision processes, and its funding and resources. The second section, Data and Model Governance, covers decisions relating to the questions of data subject consent, privacy, and model release., Comment: 12 pages, related papers arXiv:2305.06161 and arXiv:2301.03988 and arXiv:2211.15533v1, learn more at https://www.bigcode-project.org/

In this talk we review jet production in a large variety of collision systems using the JETSCAPE event generator and Hybrid Hadronization. Hybrid Hadronization combines quark recombination, applicable when distances between partons in phase space are small, and string fragmentation appropriate for dilute parton systems. It can therefore smoothly describe the transition from very dilute parton systems like $e^++e^-$ to full $A+A$ collisions. We test this picture by using JETSCAPE to generate jets in various systems. Comparison to experimental data in $e^++e^-$ and $p+p$ collisions allows for a precise tuning of vacuum baseline parameters in JETSCAPE and Hybrid Hadronization. Proceeding to systems with jets embedded in a medium, we study in-medium hadronization for jet showers. We quantify the effects of an ambient medium, focusing in particular on the dependence on the collective flow and size of the medium. Our results clarify the effects we expect from in-medium hadronization of jets on observables like fragmentation functions, hadron chemistry and jet shape., Comment: 6 pages, 4 figures, Hard Probes 2023 conference, accepted for publication in Proceedings of Science: version 2, references added, typos fixed

The photon emission from the late stages of the dynamical evolution of heavy-ion reactions at the highest RHIC and LHC energies is investigated. A comparison between a calculation from hadronic rates from a fluid dynamic evolution down to temperatures of 120 MeV and a full non-equilibrium hadronic transport approach is performed. The photon yields are very similar in both cases while the elliptic flow is slightly smaller in the non-equilibrium scenario. This study is important, since it is crucial to apply the same dynamical evolution model for hadronic and electromagnetic observables., Comment: 6 pages, 4 figures, accepted in PoS for Hard Probes 2023

Heavy-ion collisions provide a window into the properties of many-body systems of deconfined quarks and gluons. Understanding the collective properties of quarks and gluons is possible by comparing models of heavy-ion collisions to measurements of the distribution of particles produced at the end of the collisions. These model-to-data comparisons are extremely challenging, however, because of the complexity of the models, the large amount of experimental data, and their uncertainties. Bayesian inference provides a rigorous statistical framework to constrain the properties of nuclear matter by systematically comparing models and measurements. This review covers model emulation and Bayesian methods as applied to model-to-data comparisons in heavy-ion collisions. Replacing the model outputs (observables) with Gaussian process emulators is key to the Bayesian approach currently used in the field, and both current uses of emulators and related recent developments are reviewed. The general principles of Bayesian inference are then discussed along with other Bayesian methods, followed by a systematic comparison of seven recent Bayesian analyses that studied quark-gluon plasma properties, such as the shear and bulk viscosities. The latter comparison is used to illustrate sources of differences in analyses, and what it can teach us for future studies., Comment: 52 pages

Artificial Intelligence (AI) systems have made remarkable progress, attaining super-human performance across various domains. This presents us with an opportunity to further human knowledge and improve human expert performance by leveraging the hidden knowledge encoded within these highly performant AI systems. Yet, this knowledge is often hard to extract, and may be hard to understand or learn from. Here, we show that this is possible by proposing a new method that allows us to extract new chess concepts in AlphaZero, an AI system that mastered the game of chess via self-play without human supervision. Our analysis indicates that AlphaZero may encode knowledge that extends beyond the existing human knowledge, but knowledge that is ultimately not beyond human grasp, and can be successfully learned from. In a human study, we show that these concepts are learnable by top human experts, as four top chess grandmasters show improvements in solving the presented concept prototype positions. This marks an important first milestone in advancing the frontier of human knowledge by leveraging AI; a development that could bear profound implications and help us shape how we interact with AI systems across many AI applications., Comment: 61 pages, 29 figures

Recent literature in the field of machine learning (ML) control has shown promising theoretical results for a Deep Neural Network (DNN) based Nonlinear Adaptive Controller (DNAC) capable of achieving trajectory tracking for nonlinear systems. Expanding on this work, this paper applies DNAC to the Attitude Control System (ACS) of a quadrotor and shows improvement to attitude control performance under disturbed flying conditions where the model uncertainty is high. Moreover, these results are noteworthy for ML control because they were achieved with no prior training data and an arbitrary system dynamics initialization; simply put, the controller presented in this paper is practically modelless, yet yields the ability to force trajectory tracking for nonlinear systems while rejecting significant undesirable model disturbances learned through a DNN. The combination of ML techniques to learn a system's dynamics and the Lyapunov analysis required to provide stability guarantees leads to a controller with applications in safety-critical systems that may undergo uncertain model changes, as is the case for most aerial systems. Experimental findings are analyzed in the final section of this paper, and DNAC is shown to outperform the trajectory tracking capabilities of PID, MRAC, and the recently developed Deep Model Reference Adaptive Control (DMRAC) schemes.

Over the past years, decentralized finance (DeFi) has been the target of numerous profit-driven crimes. However, until now, the full prevalence and cumulative impact of these crimes have not been assessed. This study provides a first comprehensive assessment of profit-driven crimes targeting the DeFi sector. To achieve this, we collected data on 1155 crime events from 2017 to 2022. Of these, 1050 were related to the DeFi industry and 105 to the centralized finance (CeFi) industry. Focusing on the former, a taxonomy was developed to clarify the similarities and differences among these crimes. All events were mapped onto the DeFi stack to assess the impacted technical layers, and the financial damages were quantified to gauge their scale. The findings show that the entire cryptoasset industry has suffered a minimum loss of US$30B, with two thirds related to centralized finance (CeFi) and one third to DeFi. Focusing solely on the latter, the results highlight that during an attack, a DeFi actor (an entity developing a DeFi technology) can serve as a direct target, as a perpetrator, or as an intermediary. The findings show that DeFi actors are the first victims of crimes targeting the DeFi industry: 52% of crime events targeted them, primarily due to technical vulnerabilities at the protocol layer, and these events accounted for 83% of all recorded financial damages. On the other hand, in 40% of crime events, DeFi actors were themselves malicious perpetrators, predominantly misusing contracts at the cryptoasset layer (e.g., rug pull scams). However, these events accounted for only 17% of all financial damages. The study's findings offer a preliminary assessment of the size and scope of crime events within the DeFi sector and highlight the vulnerable position of DeFi actors in the ecosystem.

We propose HydraScreen, a deep-learning approach that aims to provide a framework for more robust machine-learning-accelerated drug discovery. HydraScreen utilizes a state-of-the-art 3D convolutional neural network, designed for the effective representation of molecular structures and interactions in protein-ligand binding. We design an end-to-end pipeline for high-throughput screening and lead optimization, targeting applications in structure-based drug design. We assess our approach using established public benchmarks based on the CASF 2016 core set, achieving top-tier results in affinity and pose prediction (Pearson's r = 0.86, RMSE = 1.15, Top-1 = 0.95). Furthermore, we utilize a novel interaction profiling approach to identify potential biases in the model and dataset to boost interpretability and support the unbiased nature of our method. Finally, we showcase HydraScreen's capacity to generalize across unseen proteins and ligands, offering directions for future development of robust machine learning scoring functions. HydraScreen (accessible at https://hydrascreen.ro5.ai) provides a user-friendly GUI and a public API, facilitating easy assessment of individual protein-ligand complexes.

Ransomware-as-a-service (RaaS) is increasing the scale and complexity of ransomware attacks. Understanding the internal operations behind RaaS has been a challenge due to the illegality of such activities. The recent chat leak of the Conti RaaS operator, one of the most infamous ransomware operators on the international scene, offers a key opportunity to better understand the inner workings of such organizations. This paper analyzes the main topic discussions in the Conti chat leak using machine learning techniques such as Natural Language Processing (NLP) and Latent Dirichlet Allocation (LDA), as well as visualization strategies. Five discussion topics are found: 1) Business, 2) Technical, 3) Internal tasking/Management, 4) Malware, and 5) Customer Service/Problem Solving. Moreover, the distribution of topics among Conti members shows that only 4% of individuals have specialized discussions while almost all individuals (96%) are all-rounders, meaning that their discussions revolve around the five topics. The results also indicate that a significant proportion of Conti discussions are non-tech related. This study thus highlights that running such large RaaS operations requires a workforce skilled beyond technical abilities, with individuals involved in various tasks, from management to customer service or problem solving. The discussion topics also show that the organization behind the Conti RaaS oper5086933ator shares similarities with a large firm. We conclude that, although RaaS represents an example of specialization in the cybercrime industry, only a few members are specialized in one topic, while the rest runs and coordinates the RaaS operation.

Understanding the modification of jets and high-$p_T$ probes in small systems requires the integration of soft and hard physics. We present recent developments in extending the JETSCAPE framework to build an event generator, which includes correlations between soft and hard partons, to study jet observables in small systems. The multi-scale physics of the collision is separated into different stages. Hard scatterings are first sampled at binary collision positions provided by the Glauber geometry. They are then propagated backward in space-time following an initial-state shower to obtain the initiating partons' energies and momenta before the collision. These energies and momenta are then subtracted from the incoming colliding nucleons for soft-particle production, modeled by the 3D-Glauber + hydrodynamics + hadronic transport framework. This new hybrid approach (X-SCAPE) includes non-trivial correlations between jet and soft particle productions in small systems. We calibrate this framework with the final state hadrons' $p_T$-spectra from low to high $p_T$ in $p$-$p$, and and then compare with the spectra in $p$-$Pb$ collisions from the LHC. We also present results for additional observables such as the distributions of event activity as a function of the hardest jet $p_T$ in forward and mid-rapidity for both $p$-$p$ and $p$-$Pb$ collisions., Comment: 6 pages, 6 figures, Proceedings of Hard Probes 2023, 26-31 March 2023 Aschaffenburg, Germany

I present an overview of photon and dilepton production in heavy-ion collisions, highlighting recent progress and ongoing challenges, with focus on hard initial scatterings, pre-equilibrium electromagnetic emission, as well as thermal and hadronic production. The potential of photons and dileptons to probe low-energy collisions is discussed briefly., Comment: 1 figure, 10 pages, contribution to Hard Probes 2023 proceedings

We study parton energy-momentum exchange with the quark gluon plasma (QGP) within a multistage approach composed of in-medium DGLAP evolution at high virtuality, and (linearized) Boltzmann Transport formalism at lower virtuality. This multistage simulation is then calibrated in comparison with high $p_T$ charged hadrons, D-mesons, and the inclusive jet nuclear modification factors, using Bayesian model-to-data comparison, to extract the virtuality-dependent transverse momentum broadening transport coefficient $\hat{q}$. To facilitate this undertaking, we develop a quantitative metric for validating the Bayesian workflow, which is used to analyze the sensitivity of various model parameters to individual observables. The usefulness of this new metric in improving Bayesian model emulation is shown to be highly beneficial for future such analyses., Comment: 24 pages, 16 figures

Shower development dynamics for a jet traveling through the quark-gluon plasma (QGP) is a multiscale process, where the heavy flavor mass is an important scale. During the high virtuality portion of the jet evolution in the QGP, emission of gluons from a heavy flavor is modified owing to heavy quark mass. Medium-induced radiation of heavy flavor is sensitive to microscopic processes (e.g. diffusion), whose virtuality dependence is phenomenologically explored in this study. In the lower virtuality part of shower evolution, i.e. when the mass is comparable to the virtuality of the parton, scattering and radiation processes of heavy quarks differ from light quarks. The effects of these mechanisms on shower development in heavy flavor tagged showers in the QGP is explored here. Furthermore, this multiscale study examines dynamical pair production of heavy flavor (via virtual gluon splittings) and their subsequent evolution in the QGP, which is not possible otherwise. A realistic event-by-event simulation is performed using the JETSCAPE framework. Energy-momentum exchange with the medium proceeds using a weak coupling recoil approach. Using leading hadron and open heavy flavor observables, differences in heavy versus light quark energy-loss mechanisms are explored, while the importance of heavy flavor pair production is highlighted along with future directions to study., Comment: 6 pages, 3 figures, contribution to the Hard Probes 2023 proceedings

We utilize event-by-event Monte Carlo simulations within the JETSCAPE framework to examine scale-dependent jet-medium interactions in heavy-ion collisions. The reduction in jet-medium interaction during the early high-virtuality stage, where the medium is resolved at a short distance scale, is emphasized as a key element in explaining multiple jet observables, particularly substructures, simultaneously. By employing the MATTER+LBT setup, which incorporates this explicit reduction of medium effects at high virtuality, we investigate jet substructure observables, such as Soft Drop groomed observables. When contrasted with existing data, our findings spotlight the significant influence of the reduction at the early high-virtuality stages. Furthermore, we study the substructure of gamma-tagged jets, providing predictive insights for future experimental analyses. This broadens our understanding of the various contributing factors involved in modifying jet substructures., Comment: 6 pages, 4 figures, contribution to the Hard Probes 2023 proceedings

Heavy-ion collisions at $\sqrt{s_\mathrm{NN}} \sim 10$ GeV probe the QCD phase diagram at large baryon densities. Because the longitudinal Lorentz contraction is small at these collision energies, understanding the dynamics during the early phase of the collision is essential for the subsequent modeling of the system evolution and for constraining the QGP transport properties at finite baryon densities. Direct photons provide undistorted information on early-stage dynamics. We model relativistic heavy-ion collisions at RHIC Beam Energy Scan energies with a hybrid dynamical approach consisting of a 3D-Glauber initial state followed by viscous hydrodynamics and hadronic transport (MUSIC + UrQMD). The implemented thermal photon emission takes into account the enhancement from finite baryon chemical potentials. We show that direct photon spectra and their anisotropic flow coefficients have a strong sensitivity to the early stage of heavy-ion collisions. Thus, they provide constraints on QGP dynamics complementary to those obtained from hadronic observables., Comment: 6 pages, 1 figure, proceedings for the 11th International Conference on Hard and Electromagnetic Probes of High-Energy Nuclear Collisions

In ultrarelativistic heavy-ion collisions, a plasma of deconfined quarks and gluons is formed within $1$ fm/c of the nuclei's impact. The complex dynamics of the collision before $\approx 1$ fm/c is often described with parametric models, which affect the predictivity of calculations. In this work, we perform a systematic analysis of LHC measurements from Pb-Pb collisions, by combining an \emph{ab-initio} model of the early stage of the collisions with a hydrodynamic model of the plasma. We obtain state-of-the-art constraints on the shear and bulk viscosity of quark-gluon plasma. We mitigate the additional cost of the ab-initio initial conditions by combining Bayesian model averaging with transfer learning, allowing us to account for important theoretical uncertainties in the hydrodynamics-to-hadron transition. We show that, despite the apparent strong constraints on the shear viscosity, metrics that balance the model's predictivity with its degree of agreement with data do not prefer a temperature-dependent specific shear viscosity over a constant value. We validate the model by comparing with discriminating observables not used in the calibration, finding excellent agreement., Comment: 7 pages, 4 figures

We extend the well-studied midrapidity TRENTo initial-conditions model to three dimensions, thus facilitating (3+1)D modeling and analysis of ultrarelativistic heavy-ion collisions at RHIC and LHC energies. TRENTo-3D is a fast, parametric model of the 3D initial-state geometry, capable of providing initial conditions for (3+1)D models of quark--gluon plasma formation and evolution. It builds on TRENTo's success at modeling the initial nuclear participant thicknesses, longitudinally extending the initial deposition to form a central fireball near midrapidity and two fragmentation regions at forward and backward rapidities. We validate the new model through a large-scale Bayesian calibration, utilizing as observables the rapidity distributions of charged hadrons. For computational efficiency the present effort employs a (1+1)D linearized approximation of ideal hydrodynamics as a stand-in for quark--gluon plasma dynamics. This calibration serves as model validation and paves the way for utilizing TRENTo-3D as an initial-conditions model for state-of-the-art simulation incorporating (3+1)D relativistic viscous hydrodynamics., Comment: 25 pages, 12 figures

The Quark-Gluon Plasma (QGP) is a unique phase of nuclear matter, theorized to have filled the Universe shortly after the Big Bang. A critical challenge in studying the QGP is that, to reconcile experimental observables with theoretical parameters, one requires many simulation runs of a complex physics model over a high-dimensional parameter space. Each run is computationally very expensive, requiring thousands of CPU hours, thus limiting physicists to only several hundred runs. Given limited training data for high-dimensional prediction, existing surrogate models often yield poor predictions with high predictive uncertainties, leading to imprecise scientific findings. To address this, we propose a new Additive Multi-Index Gaussian process (AdMIn-GP) model, which leverages a flexible additive structure on low-dimensional embeddings of the parameter space. This is guided by prior scientific knowledge that the QGP is dominated by multiple distinct physical phenomena (i.e., multiphysics), each involving a small number of latent parameters. The AdMIn-GP models for such embedded structures within a flexible Bayesian nonparametric framework, which facilitates efficient model fitting via a carefully constructed variational inference approach with inducing points. We show the effectiveness of the AdMIn-GP via a suite of numerical experiments and our QGP application, where we demonstrate considerably improved surrogate modeling performance over existing models.

The Gubser solution to inviscid relativistic fluid dynamics is used to examine the role of transverse expansion on the energy spectrum of photons radiated by quark-gluon plasma. Transverse flow is shown to be a modest effect on the energy spectrum of photons as a whole, despite its large effect on rare high-energy photons produced at low temperatures. An exact expression is derived for the volume of the plasma as a function of its temperature. A simple formula is obtained for the energy spectrum of high-energy thermal photons, which is used to relate the inverse slope $T_{\textrm{eff}}$ of the photon spectrum at energy $E$ to the maximum temperature of the plasma $T_0$, finding $T_{\textrm{eff}} \approx T_0/(1+\frac{5}{2} \frac{T_0}{E})$., Comment: 6 pages, 5 figures; v3: some clarifications in the text and figures; matches published version

This paper describes a methodology for learning flight control systems from human demonstrations and interventions while considering the estimated uncertainty in the learned models. The proposed approach uses human demonstrations to train an initial model via imitation learning and then iteratively, improve its performance by using real-time human interventions. The aim of the interventions is to correct undesired behaviors and adapt the model to changes in the task dynamics. The learned model uncertainty is estimated in real-time via Monte Carlo Dropout and the human supervisor is cued for intervention via an audiovisual signal when this uncertainty exceeds a predefined threshold. This proposed approach is validated in an autonomous quadrotor landing task on both fixed and moving platforms. It is shown that with this algorithm, a human can rapidly teach a flight task to an unmanned aerial vehicle via demonstrating expert trajectories and then adapt the learned model by intervening when the learned controller performs any undesired maneuver, the task changes, and/or the model uncertainty exceeds a threshold, Comment: IFAC 2023