QCD-aware recursive neural networks for jet physics
Open accessThe DOI matches its Crossref record; 33 of the 37 references it cites were found in a registry or an index, and 4 are not checked yet.
Abstract
Recent progress in applying machine learning for jet physics has been built upon an analogy between calorimeters and images. In this work, we present a novel class of recursive neural networks built instead upon an analogy between QCD and natural languages. In the analogy, four-momenta are like words and the clustering history of sequential recombination jet algorithms is like the parsing of a sentence. Our approach works directly with the four-momenta of a variable-length set of particles, and the jet-based tree structure varies on an event-by-event basis. Our experiments highlight the flexibility of our method for building task-specific jet embeddings and show that recursive architectures are significantly more accurate and data efficient than previous image-based networks. We extend the analogy from individual jets (sentences) to full events (paragraphs), and show for the first time an event-level classifier operating on all the stable particles produced in an LHC event.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“RvNN has been employed in several applications [60–62].”
From Review of deep learning: concepts, CNN architectures, challenges, applications, future directions (2021) · cites this paper as [60]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
Chung, J., Gulcehre, C., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1412.3555 · Cited by 11,008
Self-citationThe anti-ktjet clustering algorithm
Cacciari, M., Salam, G. P., & Soyez, G. (2008) · Journal of High Energy Physics · doi:10.1088/1126-6708/2008/04/063 · Cited by 7,140
Sjöstrand, T., Ask, S., Christiansen, J. R., Corke, R., Desai, N., Ilten, P., Mrenna, S., Prestel, S., Rasmussen, C. O., & Skands, P. Z. (2015) · Computer Physics Communications · doi:10.1016/j.cpc.2015.01.024 · Cited by 5,462
DELPHES 3: a modular framework for fast simulation of a generic collider experiment
The DELPHES 3 collaboration, de Favereau, J., Delaere, C., Demin, P., Giammanco, A., Lemaître, V., Mertens, A., & Selvaggi, M. (2014) · Journal of High Energy Physics · doi:10.1007/jhep02(2014)057 · Cited by 2,966
Deep Convolutional Networks on Graph-Structured Data
Henaff, M., Bruna, J., & LeCun, Y. (2015) · arXiv · doi:10.48550/arxiv.1506.05163 · Cited by 1,255
Longitudinally-invariant k⊥-clustering algorithms for hadron-hadron collisions
Catani, S., Dokshitzer, Y. L., Seymour, M. H., & Webber, B. R. (1993) · Nuclear Physics B · doi:10.1016/0550-3213(93)90166-m · Cited by 1,187
Better jet clustering algorithms
Dokshitzer, Y. L., Leder, G. D., Moretti, S., & Webber, B. R. (1997) · Journal of High Energy Physics · doi:10.1088/1126-6708/1997/08/001 · Cited by 1,062
Identifying boosted objects with N-subjettiness
Thaler, J., & Van Tilburg, K. (2011) · Journal of High Energy Physics · doi:10.1007/jhep03(2011)015 · Cited by 881
Learning task-dependent distributed representations by backpropagation through structure
Goller, C., & Kuchler, A. (2002) · Proceedings of International Conference on Neural Networks (ICNN'96) · doi:10.1109/icnn.1996.548916 · Cited by 581
Salam, G. P. (2010) · The European Physical Journal C · doi:10.1140/epjc/s10052-010-1314-6 · Cited by 431
Research works printed but not linked: 25
- R. Socher, C.C. Lin, C. Manning and A.Y. Ng, Parsing natural scenes and natural language with recursive neural networks, in Proceedings of the 28th international conference on machine learning (ICML-11), Bellevue U.S.A. (2011), pg. 129.
- R. Socher, J. Pennington, E.H. Huang, A.Y. Ng and C.D. Manning, Semi-supervised recursive autoencoders for predicting sentiment distributions, in Proceedings of the Conference on Empirical Methods in Natural Language Processing, Edinburgh U.K. (2011), pg. 151.
- K. Cho, B. van Merriënboer, D. Bahdanau and Y. Bengio, On the properties of neural machine translation: Encoder-decoder approaches, arXiv:1409.1259. · arXiv
- K. Cho et al., Learning phrase representations using rnn encoder-decoder for statistical machine translation, arXiv:1406.1078. · arXiv
- I. Goodfellow, Y. Bengio and A. Courville, Deep Learning, MIT Press, Cambridge U.S.A. (2016).
- V. Nair and G.E. Hinton, Rectified linear units improve restricted boltzmann machines, in Proceedings of the 27th international conference on machine learning (ICML-10), Haifa Israel (2010), pg. 807.
- D.P. Kingma and J. Ba, Adam: A Method for Stochastic Optimization, arXiv:1412.6980 [INSPIRE]. · arXiv
- S. R. Bowman, C. D. Manning and C. Potts, Tree-structured composition in neural networks without tree-structured architectures, arXiv:1506.04834. · arXiv
- S.R. Bowman, Modeling natural language semantics in learned representations, Ph.D. Thesis, Stanford University, Stanford U.S.A. (2016).
- G. Louppe, M. Kagan and K. Cranmer, Learning to Pivot with Adversarial Networks, arXiv:1611.01046 [INSPIRE]. · arXiv
- A.J. Larkoski, I. Moult and B. Nachman, Jet Substructure at the Large Hadron Collider: A Review of Recent Advances in Theory and Machine Learning, arXiv:1709.04464 [INSPIRE]. · arXiv
- M. Russell, Top quark physics in the Large Hadron Collider era, Ph.D. Thesis, Glasgow University, Glasgow U.K. (2017) [arXiv:1709.10508] [INSPIRE]. · arXiv
- S. Egan, W. Fedorko, A. Lister, J. Pearkes and C. Gay, Long Short-Term Memory (LSTM) networks with jet constituents for boosted top tagging at the LHC, arXiv:1711.09059 [INSPIRE]. · arXiv
- I. Henrion et al., Neural Message Passing for Jet Physics, in Proceedings of the Deep Learning for Physical Sciences Workshop at NIPS (2017), Long Beach U.S.A. (2017), https://dl4physicalsciences.github.io/files/nips dlps 2017 29.pdf. JHEP01(2019)057
- S. Choi, S.J. Lee and M. Perelstein, Infrared Safety of a Neural-Net Top Tagging Algorithm, arXiv:1806.01263 [INSPIRE]. · arXiv
- R.T. D'Agnolo and A. Wulzer, Learning New Physics from a Machine, arXiv:1806.02350 [INSPIRE]. · arXiv
- A. Andreassen, I. Feige, C. Frye and M.D. Schwartz, JUNIPR: a Framework for Unsupervised Machine Learning in Particle Physics, arXiv:1804.09720 [INSPIRE]. · arXiv
- S.R. Bowman, J. Gauthier, A. Rastogi, R. Gupta, C.D. Manning and C. Potts, A fast unified model for parsing and sentence understanding, arXiv:1603.06021. · arXiv
- D. Yogatama, P. Blunsom, C. Dyer, E. Grefenstette and W. Ling, Learning to compose words into sentences with reinforcement learning, arXiv:1611.09100. · arXiv
- J. Bruna, W. Zaremba, A. Szlam and Y. LeCun, Spectral networks and locally connected networks on graphs, arXiv:1312.6203. · arXiv
- Y. Li, D. Tarlow, M. Brockschmidt and R.S. Zemel, Gated graph sequence neural networks, arXiv:1511.05493. · arXiv
- M. Niepert, M. Ahmed and K. Kutzkov, Learning convolutional neural networks for graphs, arXiv:1605.05273. · arXiv
- M. Defferrard, X. Bresson and P. Vandergheynst, Convolutional neural networks on graphs with fast localized spectral filtering, arXiv:1606.09375. · arXiv
- T.N. Kipf and M. Welling, Semi-supervised classification with graph convolutional networks, arXiv:1609.02907. · arXiv
- T.N. Kipf and M. Welling, Semi-supervised classification with graph convolutional networks, arXiv:1609.02907. · arXiv
Cited by
Items 201–249 of 249
Probing Undiscovered Particles with Theory and Data-Driven Tools
Fraser, K. (2024) · Digital Access to Scholarship at Harvard (DASH) (Harvard University) · Cited by 1
Free-Form Flows: Generative Models for Scientific Applications
Sorrenson, P. (2025) · heiDOK (Heidelberg University) · doi:10.11588/heidok.00035980 · Cited by 1
Reinforced sorting networks for particle physics analyses
Erdmann, M., Fischer, B., & Noll, D. (2020) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1525/1/012098 · Cited by 1
Wang, X., Cai, Y., & Li, F. (2024) · Chinese Physics B · doi:10.1088/1674-1056/ad7e9a · Cited by 1
libGroomRL: Reinforcement Learning for JetsPreprint
Carrazza, S., & Dreyer, F. A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.00410 · Cited by 1
Precision Physics in Extensions of the Standard Model
Waite, P. (2019) · Durham e-Theses (Durham University) · Cited by 1
KIGNet: Physics-Motivated Multi-Graph Representation Learning for Explainable Jet TaggingPreprint
Islam, M. R., Khan, A., Hossain, M. S., Siddiqui, C. B. Y., Hossan, M. S., Khan, T., Momen, M. A., Ali, A. A., & Rahman, A. M. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2512.07420 · Cited by 1
Nachman, B. (2020) · SciPost Physics · doi:10.21468/scipost.report.1725
Andrews, M. B. (2023) · Springer theses · doi:10.1007/978-3-031-25091-0_4
Bollweg, S., Haußmann, M., Kasieczka, G., et al. (2019) · SciPost Physics · doi:10.21468/scipost.report.989
Bollweg, S., Haußmann, M., Kasieczka, G., et al. (2019) · SciPost Physics · doi:10.21468/scipost.report.1019
Bollweg, S., Haußmann, M., Kasieczka, G., et al. (2019) · SciPost Physics · doi:10.21468/scipost.report.1342
Bernreuther, E., Finke, T., Kahlhoefer, F., Krämer, M., & Mück, A. (2020) · SciPost Physics · doi:10.21468/scipost.report.1886
Zhang, J., He, W., & Ma, L. R. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.02225
Generative Machine Learning for Simulation-based Inference in High Energy Physics
Hütsch, N. K. (2025) · heiDOK (Heidelberg University) · doi:10.11588/heidok.00037074
(2024) · SciPost Physics Core · doi:10.21468/scipost.report.9017
Guo, Z. J. (2019) · theses.fr (ABES) · doi:10.70675/1a05eccbzd776z4e98zaa72zce66a738b99e
The Lund Jet Plane: An Overarching Tool
Marzani, S., Grégory Soyez, A., & Spannowsky, M. (2026) · Lecture notes in physics · doi:10.1007/978-3-032-27190-7_10
Report on scipost_202101_00010v1
(2021) · SciPost Physics · doi:10.21468/scipost.report.2643
Report on scipost_202507_00056v2
(2026) · SciPost Physics · doi:10.21468/scipost.report.12625
Report on scipost_202507_00056v1
(2025) · SciPost Physics · doi:10.21468/scipost.report.11742
(2025) · SciPost Physics · doi:10.21468/scipost.report.11223
Symmetry-aware networks for the LHC
Spinner, J. (2025) · heiDOK (Heidelberg University) · doi:10.11588/heidok.00036846
Energy Flow in Particle CollisionsPreprint
Metodiev, E. M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.04910
Take-Home Messages and Perspectives
Marzani, S., Grégory Soyez, A., & Spannowsky, M. (2019) · Lecture notes in physics · doi:10.1007/978-3-030-15709-8_11
Precision calculations in the Higgs sector within and beyond the Standard Model
Capozi, M. (2020) · Elektronische Hochschulschriften der LMU München (Ludwig-Maximilians-Universität München) · doi:10.5282/edoc.26826
Faltermann, N. (2018) · Repository KITopen (Karlsruhe Institute of Technology) · doi:10.5445/ir/1000085709
(2019) · SciPost Physics · doi:10.21468/scipost.report.1160
(2019) · SciPost Physics · doi:10.21468/scipost.report.962
(2019) · SciPost Physics · doi:10.21468/scipost.report.910
(2019) · SciPost Physics · doi:10.21468/scipost.report.809
(2018) · SciPost Physics · doi:10.21468/scipost.report.613
(2018) · SciPost Physics · doi:10.21468/scipost.report.380
(2021) · SciPost Physics · doi:10.21468/scipost.report.2578
(2020) · SciPost Physics · doi:10.21468/scipost.report.1767
(2020) · SciPost Physics · doi:10.21468/scipost.report.2170
Report on scipost_202108_00046v1
(2021) · SciPost Physics · doi:10.21468/scipost.report.3753
Report on scipost_202108_00046v2
(2022) · SciPost Physics · doi:10.21468/scipost.report.4219
Report on scipost_202403_00033v1
(2024) · SciPost Physics · doi:10.21468/scipost.report.9147
Report on scipost_202403_00033v2
(2024) · SciPost Physics · doi:10.21468/scipost.report.10030
(2024) · SciPost Physics Core · doi:10.21468/scipost.report.9116
Interaction networks for the identification of Higgs boson decays to bottom quark-antiquark pairs
Moreno, E. A., Cerri, O., Ngyuen, T. Q., Vlimant, J.-R., Newman, H. B., Periwal, A., Serikova, A., Spiropulu, M., Duarte, J. M., & Pierini, M. (2019) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.3895047
Rethinking Physics in the Age of Deep Learning
Cranmer, K. S. (2017) · Figshare · doi:10.6084/m9.figshare.5639239
Self-citationProbing new physics using initial state radiation jets at the Large Hadron Collider
Mantilla Suarez, C. A. (2020) · CERN Document Server (European Organization for Nuclear Research)
Investigating jet physics through machine learning-enhanced representation
Cerro, G. (2025) · ePrints Soton (University of Southampton)
Take-Home Messages and Perspectives
Marzani, S., Grégory Soyez, A., & Spannowsky, M. (2026) · Lecture notes in physics · doi:10.1007/978-3-032-27190-7_12
Evidential Deep Learning for uncertainty quantification in jet tagging deep neural network model
Wang, X. (2024) · Illinois Digital Environment for Access to Learning and Scholarship (University of Illinois at Urbana-Champaign)
Aspects of $\mathcal{N}=2$ SUSY gauge theories and applications to Quantum Field Theory and GravityPreprint
Cipriani, A. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.15619
Metadata
- Authors
- Louppe, G., Cho, K., Becot, C., & Cranmer, K.
- Affiliations
- New York University (US)
- Corresponding author
- Cranmer, Kyle
- Venue
- Journal of High Energy Physics
- Published
- 2019-01
- Volume
- 2019
- Issue
- 1
- ISSN
- 1029-8479 (ISSN-L)
- OpenAlex
- W2586765566
- Cited by
- 123
- References
- 36
- Citations by year
- 2026: 6 · 2025: 11 · 2024: 12 · 2023: 14 · 2022: 15 · 2021: 17 · 2020: 31 · 2019: 17
- FWCI
- 10.38
- Type
- journal article
- Language
- en
- Open access
- diamond
- doi.org
- Licence
- cc-by
- creativecommons.org/licenses/by/4.0/ (tdm)
- creativecommons.org/licenses/by/4.0/ (vor, 6 d)
- Locations
- Journal of High Energy Physics (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- ORBi (University of Liège) (submittedVersion, other-oa)
- arXiv (Cornell University)
- Funders
- National Science Foundation (1505463, 1450310, 1205376)
- Topics
- Physical Sciences › Physics and Astronomy › Nuclear and High Energy Physics › Particle physics theoretical and experimental studies
- Physical Sciences › Physics and Astronomy › Nuclear and High Energy Physics › High-Energy Particle Collisions Research
- Physical Sciences › Physics and Astronomy › Nuclear and High Energy Physics › Particle Detector Development and Performance
- Keywords
- recursive neural networks, jet physics, QCD, four-momentum, jet clustering, data efficiency
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.