arXiv subjects

Cyrin Neeraj

Publications and source records attributed to Cyrin Neeraj.

14 recordsLinked to original sources

arXiv2025

Tagging fully hadronic exotic decays of the vectorlike $\mathbf{B}$ quark using a graph neural network

Following up on our earlier study in [J. Bardhan et al., Machine learning-enhanced search for a vectorlike singlet B quark decaying to a singlet scalar or pseudoscalar, Phys. Rev. D 107 (2023) 115001; arXiv:2212.02442], we investigate the LHC prospects of pair-produced vectorlike $B$ quarks decaying exotically to a new gauge-singlet (pseudo)scalar field $\Phi$ and a $b$ quark. After the electroweak symmetry breaking, the $\Phi$ decays predominantly to $gg/bb$ final states, leading to a fully hadronic $2b+4j$ or $6b$ signature. Because of the large Standard Model background and the lack of leptonic handles, it is a difficult channel to probe. To overcome the challenge, we employ a hybrid deep learning model containing a graph neural network followed by a deep neural network. We estimate that such a state-of-the-art deep learning analysis pipeline can lead to a performance comparable to that in the semi-leptonic mode, taking the discovery (exclusion) reach up to about $M_B=1.8\:(2.4)$ TeV at HL-LHC when $B$ decays fully exotically, i.e., BR$(B \to b\Phi) = 100\%$.

hep-ph↗

arXiv2025

HEP-JEPA: A foundation model for collider physics using joint embedding predictive architecture

We present a transformer architecture-based foundation model for tasks at high-energy particle colliders such as the Large Hadron Collider. We train the model to classify jets using a self-supervised strategy inspired by the Joint Embedding Predictive Architecture. We use the JetClass dataset containing 100M jets of various known particles to pre-train the model with a data-centric approach -- the model uses a fraction of the jet constituents as the context to predict the embeddings of the unseen target constituents. Our pre-trained model fares well with other datasets for standard classification benchmark tasks. We test our model on two additional downstream tasks: top tagging and differentiating light-quark jets from gluon jets. We also evaluate our model with task-specific metrics and baselines and compare it with state-of-the-art models in high-energy physics. Project site: https://hep-jepa.github.io/

cs.LG↗

arXiv2024

TooLQit: Leptoquark Models and Limits

We introduce the leptoquark (LQ) toolkit, TooLQit, which includes leading-order FeynRules models for all types of LQs and a Python-based calculator, named CaLQ, to test if a set of parameter points are allowed by the LHC dilepton searches. The models include electroweak gauge interactions of the LQs and follow a set of intuitive notations. Currently, CaLQ can calculate the LHC limits on LQ ($S_1$ and $U_1$) couplings (one or more simultaneously) for any mass between $1$ and $5$ TeV using a $\chi^2$ method. In this manual for TooLQit, we describe the FeynRules models and discuss the techniques used in CaLQ. We outline the workflow to check parameter spaces of LQ models with an example. We show some illustrative scans for one- and multi-coupling scenarios for the $U_1$ vector LQ. The TooLQit code is available at https://github.com/rsrchtsm/TooLQit

hep-ph↗

arXiv2024

Constructing sensible baselines for Integrated Gradients

Machine learning methods have seen a meteoric rise in their applications in the scientific community. However, little effort has been put into understanding these "black box" models. We show how one can apply integrated gradients (IGs) to understand these models by designing different baselines, by taking an example case study in particle physics. We find that the zero-vector baseline does not provide good feature attributions and that an averaged baseline sampled from the background events provides consistently more reasonable attributions.

cs.LG↗

arXiv2024

Loss function to optimise signal significance in particle physics

We construct a surrogate loss to directly optimise the significance metric used in particle physics. We evaluate our loss function for a simple event classification task using a linear model and show that it produces decision boundaries that change according to the cross sections of the processes involved. We find that the models trained with the new loss have higher signal efficiency for similar values of estimated signal significance compared to ones trained with a cross-entropy loss, showing promise to improve sensitivity of particle physics searches at colliders.

hep-ph↗

arXiv2024

Unsupervised and lightly supervised learning in particle physics

We review the main applications of machine learning models that are not fully supervised in particle physics, i.e., clustering, anomaly detection, detector simulation, and unfolding. Unsupervised methods are ideal for anomaly detection tasks -- machine learning models can be trained on background data to identify deviations if we model the background data precisely. The learning can also be partially unsupervised when we can provide some information about the anomalies at the data level. Generative models are useful in speeding up detector simulations -- they can mimic the computationally intensive task without large resources. They can also efficiently map detector-level data to parton-level data (i.e., data unfolding). In this review, we focus on interesting ideas and connections and briefly overview the underlying techniques wherever necessary.

hep-ph↗

arXiv2024

Pinning down the leptophobic $Z^\prime$ in leptonic final states with Deep Learning

A leptophobic $Z^\prime$ that does not couple with the Standard Model leptons can evade the stringent bounds from the dilepton-resonance searches. In our earlier paper [T. Arun et al., Search for the $Z'$ boson decaying to a right-handed neutrino pair in leptophobic $U(1)$ models, Phys. Rev. D, 106 (2022) 095035; arXiv:2204.02949], we presented two gauge anomaly-free $U(1)$ models -- one based on the Green-Schwarz (GS) anomaly cancellation mechanism, and the other on a grand unified theory (GUT) framework with gauge kinetic mixing -- where a heavy leptophobic $Z'$ is present along with right-handed neutrinos ($N_R$). We pointed out the interesting possibility of a correlated search for $Z'$ and $N_R$ at the LHC through the $pp\to Z'\to N_R N_R$ channel. This channel can probe a part of the $Z'$ parameter space beyond the reach of the standard dijet resonance searches. In this follow-up paper, we analyse the challenging monolepton final state arising from the decays of the $N_R$ pair with Deep Learning. We present the high-luminosity LHC discovery reaches for six different GUT embeddings and a benchmark point in the GS setup. We also update our previous estimates in the dilepton channel with Deep Learning. We identify parameter regions that can be probed with the proposed channel but will remain inaccessible to dijet searches at the HL-LHC.

hep-ph↗

arXiv2023

Machine learning-enhanced search for a vectorlike singlet $B$ quark decaying to a singlet scalar or pseudoscalar

The presence of a new decay mode relaxes the current mass exclusion limits on vectorlike quarks considerably. We consider the case of a weak-singlet vectorlike $B$ quark that can decay to a singlet scalar or pseudoscalar $Φ$. In an earlier paper [A. Bhardwaj et al., Roadmap to explore vectorlike quarks decaying to a new scalar or pseudoscalar, Phys. Rev. D, 106 (2022) 095014; arXiv:2203.13753], we mapped the possibilities to explore such setups at the LHC. We showed that it is possible for a $B$ quark to decay into $Φ$ and the $Φ$ to dominantly decay to a pair of gluons or $b$ quark(s) without fine-tuning the parameters. In this paper, we present a collider search strategy to look for the pair production of singlet $B$ quarks. If both $B$ quarks decay into $bΦ$ pairs, the final state is fully hadronic: $B{B}\to(bΦ)({b}Φ)\to (bgg)({b}gg)/(bb{b})({b}b{b})$, which is very challenging to probe. Therefore, we consider a simpler mixed decay specific to the singlet $B$ case, $BB\to(bΦ)(tW)$ with a lepton in the final state, to achieve the best sensitivity at the high-luminosity LHC. We use a deep neural network with a weighted cross-entropy loss to separate the signal from the huge SM background. Our analysis shows that large areas of the $M_{B}-M_Φ$ parameter space are discoverable through this signature. We show how the discovery and exclusion regions scale with the branching ratio in the new decay mode. We also estimate the reach in the inclusive monolepton channel with the same network model.

hep-ph↗

arXiv2022

Discovery prospects of a vectorlike top partner decaying to a singlet boson

The possibility of a vectorlike top partner decaying to a new colourless weak-singlet scalar or pseudoscalar has attracted some attention in the literature. We investigate the production of a weak-singlet charge-$2/3$ $T$ quark that can decay to a spinless boson ($Φ$) and a top quark at the LHC. Earlier, in 2203.13753, we have shown that in a large part of the parameter space, the $T\to tΦ$ and the loop-induced $Φ\to gg$ decays become the dominant decay modes for these particles. Here, we investigate the discovery prospects of the $T$ quark in this region through the above decays. In particular, we focus on the $pp\to TT\to (tΦ)(tΦ)\to (t(gg))\,(t(gg))$ channel. Separating this signal from the huge Standard Model background is a challenging task, forcing us to employ a multivariate machine-learning technique. We find that the above channel can be a discovery channel of the top partner in the large part of the parameter space where the above decay chain dominates. Our analysis is largely model-independent, and hence our results would be useful in a broad class of new physics models.

hep-ph↗

arXiv2022

Roadmap to explore vectorlike quarks decaying to a new scalar or pseudoscalar

The current experimental data allow for a sub-TeV colourless weak-singlet scalar or pseudoscalar. If such a singlet field is present together with TeV-range vectorlike top and bottom partners, there is a possibility that the heavy quarks decay dominantly to the singlet state and a third-generation quark, and the singlet state decays to quark and boson pairs. Such a possibility may arise in various models but it has not been explored experimentally, especially in the context of vectorlike-quark searches. We consider some minimal models, covering the possible weak representations of the top and bottom partners, that can be mapped to many well-motivated ultraviolet-complete theories. We chart out the possible interesting and unexplored signatures of the exotic decay of vectorlike quarks and identify benchmark points representing different signal topologies for the high luminosity LHC. We perform a general scan of the parameter space with the relevant direct search bounds and find that large regions, which do not require any fine-tuning, remain open for the unexplored channels. We also perform a simple projection study in the cleanest channel and indicate how other new but experimentally challenging channels can be used to probe more regions of the parameter space.

hep-ph↗

arXiv2022

Leptoquark-assisted Singlet-mediated Di-Higgs Production at the LHC

At the LHC, the gluon-initiated processes are considered to be the primary source of di-Higgs production. However, in the presence of a new resonance, the light-quark initiated processes can also contribute significantly. In this paper, we look at the di-Higgs production mediated by a new singlet scalar. The singlet is produced in both quark-antiquark and gluon fusion processes through loops involving a scalar leptoquark and right-handed neutrinos. With benchmark parameters inspired from the recent resonant di-Higgs searches by the ATLAS collaboration, we examine the prospects of such a resonance in the TeV-range at the High-Luminosity LHC (HL-LHC) in the $b\bar{b} τ^{+}τ^{-}$ mode with a multivariate analysis. We obtain the $5σ$ and $2σ$ contours and find that a significant part of the parameter space is within the reach of the HL-LHC.

hep-ph↗

arXiv2022

Precise LHC limits on the $\rm{U}_1$ leptoquark parameter space

A TeV scale leptoquark (LQ) is one of the promising explanations of the recent anomalies in the semileptonic decays of $B$ mesons. Among the various LQs, the vector $\rm{U}_1$ is capable of explaining the anomalies in both $R_{D^{(*)}}$ and $R_{K^{(*)}}$ observables. We use the current LHC data to put bounds on the parameter space of $\rm{U}_1$ relevant for the anomalies. Precise bounds are drawn by recasting the latest $ττ$ and $μμ$ searches by the ATLAS and CMS collaborations. We find that it is imperative to include the resonant production modes for obtaining limits in the low mass regions. For higher mass points, the non-resonant production modes play a dominant role.

hep-ph↗

arXiv2021

Precise limits on the charge-$2/3$ $U_1$ vector leptoquark

The $U_1$ leptoquark is known to be a suitable candidate for explaining the semileptonic $B$-decay anomalies. We derive precise limits on its parameter space relevant for the anomalies from the current LHC high-$p_{\rm T}$ dilepton data. We consider an exhaustive list of possible $B$-anomalies-motivated simple scenarios with one or two new couplings that can also be used as templates for obtaining bounds on more complicated scenarios. To obtain precise limits, we systematically consider all possible $U_1$ production processes that can contribute to the dilepton searches, including the resonant pair and single productions, nonresonant $t$-channel $U_1$ exchange, as well as its large interference with the Standard Model background. We demonstrate how the inclusion of resonant production contributions in the dilepton signal can lead to appreciably improved exclusion limits. We point out new search channels of $U_1$ that can act as unique tests of the flavour-motivated models. The template scenarios can also be used for future $U_1$ searches at the LHC. We compare the LHC limits with other relevant flavour bounds and find that a TeV-scale $U_1$ can accommodate both $R_{D^{(*)}}$ and $R_{K^{(*)}}$ anomalies while satisfying all the bounds.

hep-ph↗

arXiv2021

LHC Bounds on $R_{D^{(*)}}$ motivated Leptoquark Models

Most of the popular explanations of the observed anomalies in the semileptonic $B$-meson decays involve TeV scale Leptoquarks (LQs). Among the various possible LQ models, two particular LQs -- $S_{1}(3, 1, 1/3)$ and $U_{1}(3, 1, 2/3)$ seem to be most promising. Here, we use current LHC data to constrain the $S_{1}(3, 1, 1/3)$ and $U_{1}(3, 1, 2/3)$ parameter spaces relevant for the $R_{D^{(*)}}$ observables. We recast the latest ATLAS $ττ$ resonance search data to obtain new exclusion limits. For this purpose, we consider both resonant (pair and single productions) and non-resonant ($t$-channel LQ exchange) productions of these LQs at the LHC. For the limits, the most dominant contribution comes from the (destructive) interference of the non-resonant production with Standard Model backgrounds. The combined contribution from the pair and inclusive single production processes is less prominent but non-negligible. The limits we get are independent and competitive to other known bounds. For both the models, we set limits on $R_{D^{(*)}}$ motivated couplings.

hep-ph↗