Cyrin Neeraj
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Cyrin Neeraj has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Subhadip Mitra
International Institute of Information Technology, Hyderabad
17 shared publications - Tanumoy Mandal
Indian Institute of Science Education and Research Thiruvananthapuram
13 shared publications - Arvind Bhaskar
Institute of Physics Sachivalaya Marg 751 005 Bhubaneswar India
6 shared publications - Diganta Das
International Institute of Information Technology
4 shared publications - Jai Bardhan
Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague
4 shared publications - Akanksha Bhardwaj
School of Physics and Astronomy, University of Glasgow, Glasgow G12 8QQ, United Kingdom
3 shared publications
Latest Publications
- Open Access
- 15 July 2025
- Published by American Physical Society (APS) in Physical Review D
- Vol. 112 (1)
Tagging fully hadronic exotic decays of the vectorlike quark using a graph neural networkFollowing up on our earlier study [J. Bardhan , ], we investigate the LHC prospects of pair-produced vectorlike B quarks decaying exotically to a new gauge-singlet (pseudo)scalar field Φ and a b quark. After the electroweak symmetry breaking, the Φ decays predominantly to g g / b b final states, leading to a fully hadronic 2 b + 4 j or 6 b 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 semileptonic 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 → b Φ ) = 100 % .
- 15 July 2025
- Published by American Physical Society (APS) in Physical Review D
- Vol. 112 (1)
Open AccessTagging fully hadronic exotic decays of the vectorlike quark using a graph neural networkFollowing up on our earlier study [J. Bardhan , ], we investigate the LHC prospects of pair-produced vectorlike B quarks decaying exotically to a new gauge-singlet (pseudo)scalar field Φ and a b quark. After the electroweak symmetry breaking, the Φ decays predominantly to g g / b b final states, leading to a fully hadronic 2 b + 4 j or 6 b 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 semileptonic 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 → b Φ ) = 100 % .
- Open Access
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.
Open AccessConstructing 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.
- Open Access
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.
Open AccessLoss 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.
- 17 July 2024
- Published by Springer Nature
- p. 514-517
Filling the Gap in the Vectorlike Quark Searches
- 8 July 2024
- Published by Springer Nature in The European Physical Journal Special Topics
- Vol. 233 (15-16) , 2559-2596
Unsupervised and lightly supervised learning in particle physics
- 8 July 2024
- Published by Springer Nature in The European Physical Journal Special Topics
- Vol. 233 (15-16) , 2559-2596
Unsupervised and lightly supervised learning in particle physics
- Open AccessPinning down the leptophobic $Z^\prime$ in leptonic final states with Deep LearningA 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.Open AccessPinning down the leptophobic $Z^\prime$ in leptonic final states with Deep LearningA 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.
- Open Access
- 22 December 2023
- Published by Elsevier in Physics Letters B
- Vol. 849
Pinning down the leptophobic Z′ in leptonic final states with Deep Learning
- 22 December 2023
- Published by Elsevier in Physics Letters B
- Vol. 849
Open AccessPinning down the leptophobic Z′ in leptonic final states with Deep Learning
- Open AccessMachine learning-enhanced search for a vectorlike singlet $B$ quark decaying to a singlet scalar or pseudoscalarThe 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 $\Phi$. 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 $\Phi$ and the $\Phi$ 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 $b\Phi$ pairs, the final state is fully hadronic: $B{B}\to(b\Phi)({b}\Phi)\to (bgg)({b}gg)/(bb{b})({b}b{b})$, which is very challenging to probe. Therefore, we consider a simpler mixed decay specific to the singlet $B$ case, $BB\to(b\Phi)(tW)$ 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 $M_{B}-M_{\Phi}$ 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.Open AccessMachine learning-enhanced search for a vectorlike singlet $B$ quark decaying to a singlet scalar or pseudoscalarThe 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 $\Phi$. 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 $\Phi$ and the $\Phi$ 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 $b\Phi$ pairs, the final state is fully hadronic: $B{B}\to(b\Phi)({b}\Phi)\to (bgg)({b}gg)/(bb{b})({b}b{b})$, which is very challenging to probe. Therefore, we consider a simpler mixed decay specific to the singlet $B$ case, $BB\to(b\Phi)(tW)$ 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 $M_{B}-M_{\Phi}$ 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.
- Open Access
- 1 June 2023
- Published by American Physical Society (APS) in Physical Review D
- Vol. 107 (11) , 115001
Machine learning-enhanced search for a vectorlike singlet quark decaying to a singlet scalar or pseudoscalarThe 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 quark that can decay to a singlet scalar or pseudoscalar . In an earlier paper [A. Bhardwaj et al., Roadmap to explore vectorlike quarks decaying to a new scalar or pseudoscalar, Phys. Rev. D, 106, 095014 (2022)], we mapped the possibilities to explore such setups at the LHC. We showed that it is possible for a quark to decay into and the to dominantly decay to a pair of gluons or quark(s) without fine-tuning the parameters. In this paper, we present a collider search strategy to look for the pair production of singlet quarks. If both ’s decay into pairs, the final state is fully hadronic: , which is very challenging to probe. Therefore, we consider a simpler mixed decay specific to the singlet case, 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 Standard Model background. Our analysis shows that large areas of the 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.- 1 June 2023
- Published by American Physical Society (APS) in Physical Review D
- Vol. 107 (11) , 115001
Open AccessMachine learning-enhanced search for a vectorlike singlet quark decaying to a singlet scalar or pseudoscalarThe 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 quark that can decay to a singlet scalar or pseudoscalar . In an earlier paper [A. Bhardwaj et al., Roadmap to explore vectorlike quarks decaying to a new scalar or pseudoscalar, Phys. Rev. D, 106, 095014 (2022)], we mapped the possibilities to explore such setups at the LHC. We showed that it is possible for a quark to decay into and the to dominantly decay to a pair of gluons or quark(s) without fine-tuning the parameters. In this paper, we present a collider search strategy to look for the pair production of singlet quarks. If both ’s decay into pairs, the final state is fully hadronic: , which is very challenging to probe. Therefore, we consider a simpler mixed decay specific to the singlet case, 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 Standard Model background. Our analysis shows that large areas of the 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. - Open Access
- 10 November 2022
- Published by American Physical Society (APS) in Physical Review D
- Vol. 106 (9) , 095014
Roadmap to explore vectorlike quarks decaying to a new scalar or pseudoscalar
The current experimental data allow for a sub-TeV colorless 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.
- 10 November 2022
- Published by American Physical Society (APS) in Physical Review D
- Vol. 106 (9) , 095014
Open AccessRoadmap to explore vectorlike quarks decaying to a new scalar or pseudoscalar
The current experimental data allow for a sub-TeV colorless 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.