pith. sign in

arxiv: 2605.17318 · v2 · pith:6NBKKVBUnew · submitted 2026-05-17 · ✦ hep-ph

RooAgent: An LLM Agent for Root-Based High Energy Physics Analysis

Aman Desai This is my paper

Pith reviewed 2026-05-20 13:27 UTC · model grok-4.3

classification ✦ hep-ph
keywords LLM agentROOThigh energy physicsnatural language interfacePyROOTdata analysisATLAS open dataHiggs analysis
0
0 comments X

The pith

RooAgent lets an LLM agent invoke PyROOT functions to run high energy physics analyses from plain-language prompts.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper presents RooAgent as a natural-language interface for ROOT-based high energy physics data analysis. Physics analysis functions are exposed as tools that the LLM selects and calls in response to user prompts. Two modes are implemented: a LangGraph agent for models such as GPT-4.1 and DeepSeek-V3, and a Model Context Protocol server for Claude. Demonstrations cover histogram inspection, event selection, kinematic distributions, fitting, and significance estimation on Monte Carlo samples of pp to ZH and on ATLAS open data for H to ZZ* to 4l. If the agent reliably performs these steps, physicists could obtain analysis results by describing the desired outcome rather than writing explicit code.

Core claim

RooAgent supplies PyROOT physics analysis functions as tools to an LLM agent that responds to plain-language prompts, supporting LangGraph and Model Context Protocol modes while keeping the analysis logic in PyROOT; the package is illustrated with Monte Carlo simulations of pp to ZH, multi-task signal-background workflows, toy statistical analyses, and an application to ATLAS open data for H to ZZ* to 4l.

What carries the argument

LLM agent that selects and supplies arguments to PyROOT analysis functions provided as tools

If this is right

  • Users can request tasks such as histogram inspection or kinematic visualization directly in natural language.
  • The system supports full workflows including event selection, fitting, and significance estimation on Monte Carlo and open data.
  • Analysis logic remains in PyROOT while different LLM backends are interchangeable through the two supported modes.
  • The package is demonstrated on standard ATLAS open data for the four-lepton Higgs channel.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • If error rates remain low, the approach could shorten the time between idea and result for routine HEP tasks.
  • Educational use might let students explore open data by describing questions rather than learning PyROOT syntax first.
  • Extending the tool set to include more advanced statistical methods could test whether the same prompting style scales to full analyses.

Load-bearing premise

That an LLM can consistently select the correct analysis tools and supply accurate arguments for non-trivial physics workflows without introducing logical or numerical errors.

What would settle it

Execute a known workflow such as event selection and significance estimation on a ZH Monte Carlo sample both via the agent and via direct PyROOT code, then compare the resulting histograms, fit parameters, and significance values for agreement.

Figures

Figures reproduced from arXiv: 2605.17318 by Aman Desai.

Figure 1
Figure 1. Figure 1: Architecture of RooAgent in the LangGraph-based operating mode. A user issues natural-language queries to an LLM-based agent, which selects and invokes the appropriate Root analysis tools and returns results as plots, statistics, tables, or summaries. The system supports iterative reasoning: tools may be called multiple times. 4 [PITH_FULL_IMAGE:figures/full_fig_p004_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Representative leading-order Feynman diagram for [PITH_FULL_IMAGE:figures/full_fig_p006_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: mbb histogram from signal.root with a logarithmic y-axis. Plots generated by RooAgent. Test 6: Normalised mll Histogram User Prompt Plot the mll histogram from background.root with normalised area and save it. Output requirements: Save all generated PDF files under output; every PDF filename must end with _test06.pdf. Elapsed time: 18.27 s Final Answer The normalised mll histogram from background.root has … view at source ↗
Figure 4
Figure 4. Figure 4: Area-normalised mℓℓ distribution from background.root. Plots generated by RooAgent. Test 7: muon_pt Distribution User Prompt Show a plot of muon_pt from the events tree in background.root. Output requirements: Save all generated PDF files under output; every PDF filename must end with _test07.pdf. Elapsed time: 12.69 s Final Answer The plot of muon_pt from the events tree in background.root has been genera… view at source ↗
Figure 5
Figure 5. Figure 5: Muon pT distribution from the events tree in background.root. Plots generated by RooAgent. Test 9: 2D Plot: jet_pt vs. jet_eta User Prompt Draw a 2D plot of jet_pt versus jet_eta from signal.root using jet_eta ∈ [−4, 4] and jet_pt ∈ [0, 100]. Output requirements: Save all generated PDF files under output; every PDF filename must end with _test09.pdf. Elapsed time: 20.50 s Final Answer The 2D plot of jet_pt… view at source ↗
Figure 6
Figure 6. Figure 6: 2D histogram of jet pT vs. jet η from the events tree in signal.root. The η range is [−4, 4] and the pT range is [0, 100] GeV, each with 40 bins. Plots generated by RooAgent. Test 10: Correlation: jet_pt vs. dilep_pt User Prompt Show the correlation between jet_pt and dilep_pt in the events tree. Output requirements: Save all generated PDF files under output; every PDF filename must end with _test10.pdf. E… view at source ↗
Figure 7
Figure 7. Figure 7: 2D histogram of dilepton pT vs. jet pT for signal events, covering [0, 100] GeV in each axis. Plots generated by RooAgent. Test 11: Event Count: dilep_pt > 50 User Prompt Count events in signal.root where dilep_pt > 50. Output requirements: Save all generated PDF files under output; every PDF filename must end with _test11.pdf. Elapsed time: 8.19 s 11 [PITH_FULL_IMAGE:figures/full_fig_p011_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: S/√ S + B significance as a function of the lower mbb threshold. The optimal cut is at mbb > 75 GeV, giving Z = 5.18. Plots generated by RooAgent. Test 16: New Variable: leading_jet_pt User Prompt Create leading_jet_pt = jet_pt[0] in the events tree of signal.root. Output requirements: Save all generated PDF files under output; every PDF filename must end with _test16.pdf. Elapsed time: 17.27 s Final Answe… view at source ↗
Figure 9
Figure 9. Figure 9: Gaussian fit to the mbb histogram from signal.root. The fitted parameters are µ = 108.32 GeV and σ = 13.23 GeV. Plots generated by RooAgent. Test 19: CSV Export of jet_pt, jet_eta, dilep_pt User Prompt Export jet_pt, jet_eta, and dilep_pt from the events tree to CSV. Output requirements: Save all generated PDF files under output; every PDF filename must end with _test19.pdf. Elapsed time: 37.63 s Final Ans… view at source ↗
Figure 10
Figure 10. Figure 10: mbb distribution overlaid for signal and background, normalised to event weights. Plots generated by RooAgent. Test 21: muon_pt Overlay: Signal vs. Background User Prompt Overlay muon_pt from signal.root and background.root in one comparison plot. Output requirements: Save all generated PDF files under output; every PDF filename must end with _test21.pdf. Elapsed time: 23.65 s Final Answer The overlay plo… view at source ↗
Figure 11
Figure 11. Figure 11: Muon pT distributions for signal and background overlaid, covering [0, 100] GeV with 40 bins. Plots generated by RooAgent. 15 [PITH_FULL_IMAGE:figures/full_fig_p015_11.png] view at source ↗
Figure 12
Figure 12. Figure 12: S/√ S + B significance as a function of the lower mbb threshold, scanned over [80, 140] GeV. The optimal cut within this range is mbb > 80 GeV, giving Z ≈ 5.17. Plots generated by RooAgent. 3.4 Multi-Task Analysis To test RooAgent on a multi-step workflow, we issued a single six-task prompt covering fitting, visu￾alisation, cutflow, cut optimisation, mass-window scanning, and cut ranking. The tasks were e… view at source ↗
Figure 13
Figure 13. Figure 13: Gaussian fit to the mbb distribution from the events tree in signal.root, covering [80, 160] GeV with 50 bins. The fitted mean is 109.5 GeV and width is 12.1 GeV. Plots generated by RooAgent. 17 [PITH_FULL_IMAGE:figures/full_fig_p017_13.png] view at source ↗
Figure 14
Figure 14. Figure 14: Normalised kinematic distributions for signal (blue) and background (red) from the [PITH_FULL_IMAGE:figures/full_fig_p018_14.png] view at source ↗
Figure 15
Figure 15. Figure 15: mbb overlay of signal and background produced for the same prompt as in test 20 using the DeepSeek-V3 [39] model via Ollama [30]. Plots generated by RooAgent. 4 Statistical Analysis with RooAgent To test the statistical tools, we constructed a toy invariant mass spectrum with a smoothly falling exponential background and Gaussian signal templates at several mass hypotheses5 . The observed data contain bac… view at source ↗
Figure 16
Figure 16. Figure 16: Statistical scan results from the toy dataset. (a) Significance, (b) p-value, and (c) CL [PITH_FULL_IMAGE:figures/full_fig_p020_16.png] view at source ↗
Figure 17
Figure 17. Figure 17: Stacked m4ℓ distribution for signal and background MC overlaid with data points after all five sequential lepton selection cuts. The MC statistical uncertainty is shown as a hatched band. The histogram covers m4ℓ ∈ [80, 170] GeV with 24 bins. The ZZ background dominates; signal yield S = 8.30, Z = 0.43. Plots generated by RooAgent. The significance Z = 0.43 is expected given no selections on m4ℓ or other … view at source ↗
Figure 18
Figure 18. Figure 18: Stacked m4ℓ distribution for signal and background MC overlaid with data points, produced by Sonnet 4.6 (claude-sonnet-4-6) via the RooAgent MCP server using the same prompt as in [PITH_FULL_IMAGE:figures/full_fig_p023_18.png] view at source ↗
read the original abstract

We present RooAgent as a natural-language interface for Root-based high energy physics data analysis. The package provides physics analysis functions as tools that an LLM agent invokes in response to plain-language prompts. Two operating modes are supported: a LangGraph-based agent compatible with OpenAI's GPT-4.1 via GitHub Copilot and with DeepSeek-V3 via Ollama, and a Model Context Protocol server for use with the Anthropic Claude CLI (Sonnet~4.6). In both modes the analysis logic is implemented in PyRoot and the LLM selects tools and supplies the required arguments. The package supports histogram inspection, event selection, visualisation of kinematic distributions, fitting, and significance estimation, among other tasks. We illustrate RooAgent with tests based on Monte Carlo simulations of $pp\to ZH$ ($Z\to\ell^+\ell^-$, $H\to b\bar{b}$), a multi-task signal-background workflow, a toy statistical analysis, and an application to ATLAS open data for $H\to ZZ^*\to 4\ell$. The package is available on PyPI and the source code is hosted at https://github.com/amanmdesai/RooAgent.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 2 minor

Summary. The manuscript presents RooAgent, a natural-language interface for ROOT-based high-energy physics data analysis. Physics analysis functions are exposed as tools that an LLM agent invokes in response to plain-language prompts. Two operating modes are supported (LangGraph-based agent with GPT-4.1 or DeepSeek-V3, and Model Context Protocol server with Claude). The package implements tasks including histogram inspection, event selection, kinematic visualization, fitting, and significance estimation in PyROOT. The authors illustrate the tool with single-run examples on pp→ZH Monte Carlo, a multi-task signal-background workflow, toy statistics, and ATLAS open data for H→ZZ*→4ℓ.

Significance. If the agent reliably selects and parameterizes tools for non-trivial multi-step analyses, RooAgent could lower the barrier to ROOT usage in HEP and accelerate prototyping for both experts and newcomers. The open-source release on PyPI and GitHub is a clear practical strength. However, the absence of quantitative evaluation metrics makes it difficult to judge whether the claimed reliability holds for realistic workflows.

major comments (1)
  1. [Results / Illustrations] The central claim that the LLM agent produces correct tool calls and arguments for multi-step physics workflows (event selection, fitting, significance) rests on illustrative single-run examples only. No success rates, error distributions, repeated-trial statistics, or failure-case analysis are reported for the Monte Carlo ZH, multi-task, toy-statistics, or ATLAS open-data demonstrations. This omission directly limits assessment of whether the approach is practically reliable.
minor comments (2)
  1. A concise table listing all available tools, their required arguments, and example natural-language prompts would improve clarity and usability.
  2. [Abstract] The abstract and introduction could more explicitly state the scope limitations (e.g., that the current implementation targets common but not exhaustive ROOT tasks).

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for their constructive feedback and for acknowledging the practical strengths of RooAgent, including its open-source availability. We address the single major comment below.

read point-by-point responses

  1. Referee: [Results / Illustrations] The central claim that the LLM agent produces correct tool calls and arguments for multi-step physics workflows (event selection, fitting, significance) rests on illustrative single-run examples only. No success rates, error distributions, repeated-trial statistics, or failure-case analysis are reported for the Monte Carlo ZH, multi-task, toy-statistics, or ATLAS open-data demonstrations. This omission directly limits assessment of whether the approach is practically reliable.

    Authors: We agree that the current presentation relies on single-run illustrative examples and lacks the quantitative metrics (success rates, error distributions, repeated-trial statistics) that would allow a more rigorous evaluation of reliability for non-trivial workflows. The manuscript frames these demonstrations as illustrations of functionality rather than as a statistical benchmark study. To address this limitation, we will revise the manuscript by adding a new subsection that reports observed success rates and common failure modes from repeated executions of the multi-task and ATLAS open-data workflows. This will include a concise table of results and a discussion of typical issues such as argument mis-specification in complex selections. revision: yes

Circularity Check

0 steps flagged

No significant circularity: software tool description

full rationale

The manuscript is a software engineering contribution that describes the RooAgent package, its two operating modes, supported physics analysis functions implemented in PyRoot, and illustrative examples on ZH Monte Carlo, multi-task workflows, toy statistics, and ATLAS open data. No equations, derivations, fitted parameters, predictions of new quantities, or load-bearing self-citations appear in the provided text. The central claims reduce only to the existence and functionality of the released code on PyPI and GitHub, which is externally verifiable and independent of any internal reduction. This is the expected finding for a non-mathematical tool paper.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

This is a software tool paper; no free parameters, axioms, or invented physical entities are introduced.

pith-pipeline@v0.9.0 · 5727 in / 1040 out tokens · 45512 ms · 2026-05-20T13:27:36.148371+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

53 extracted references · 53 canonical work pages · 21 internal anchors

  1. [1]

    Brun and F

    R. Brun and F. Rademakers,ROOT — An object oriented data analysis framework,Nucl. Instrum. Meth. A389(1997) 81–86

    work page 1997

  2. [2]

    Galli, E

    M. Galli, E. Tejedor and S. Wunsch,A New PyROOT: Modern, Interoperable and More Pythonic, EPJ Web Conf.245(2020) 06004

    work page 2020

  3. [3]

    W. X. Zhao, K. Zhou, J. Li, T. Tang, X. Wang, Y. Hou et al.,A Survey of Large Language Models, 2303.18223

    work page internal anchor Pith review Pith/arXiv arXiv

  4. [4]

    Toolformer: Language Models Can Teach Themselves to Use Tools

    T. Schick, J. Dwivedi-Yu, R. Dessì, R. Raileanu, M. Lomeli, E. Hambro et al.,Toolformer: Language models can teach themselves to use tools,Advances in Neural Information Processing Systems36(2023) 68539–68551, [2302.04761]

    work page internal anchor Pith review Pith/arXiv arXiv 2023

  5. [5]

    Talm: Tool augmented language models.arXiv preprint arXiv:2205.12255, 2022

    A. Parisi, Y. Zhao and N. Fiedel,TALM: Tool Augmented Language Models,2205.12255

    work page arXiv

  6. [6]

    Radovic, M

    A. Radovic, M. Williams, D. Rousseau, M. Kagan, D. Bonacorsi, A. Himmel et al.,Machine learning at the energy and intensity frontiers of particle physics,Nature560(2018) 41–48

    work page 2018

  7. [7]

    Deep Learning and its Application to LHC Physics

    D. Guest, K. Cranmer and D. Whiteson,Deep Learning and its Application to LHC Physics,Ann. Rev. Nucl. Part. Sci.68(2018) 161–181, [1806.11484]

    work page internal anchor Pith review Pith/arXiv arXiv 2018

  8. [8]

    Machine Learning in High Energy Physics Community White Paper

    K. Albertsson et al.,Machine Learning in High Energy Physics Community White Paper,J. Phys. Conf. Ser.1085(2018) 022008, [1807.02876]

    work page internal anchor Pith review Pith/arXiv arXiv 2018

  9. [9]

    A Living Review of Machine Learning for Particle Physics

    M. Feickert and B. Nachman,A Living Review of Machine Learning for Particle Physics, 2102.02770

    work page arXiv

  10. [10]

    Plehn, A

    T. Plehn, A. Butter, B. Dillon, T. Heimel, C. Krause and R. Winterhalder,Modern Machine Learning for LHC Physicists,2211.01421

    work page arXiv

  11. [11]

    J. Jiao, T. Liu, K. Li, W. Song, Y. Liao, B. Zhang et al.,HepScript: A Dual-Use DSL for Human-AI Collaborative Data Analysis Workflows in High-Energy Physics,2605.01423

    work page internal anchor Pith review Pith/arXiv arXiv

  12. [12]

    Zhang et al.,Xiwu: A Basis Flexible and Learnable LLM for High Energy Physics,2404.08001

    Z. Zhang et al.,Xiwu: A Basis Flexible and Learnable LLM for High Energy Physics,2404.08001. [13]Electron-Positron Alliancecollaboration, A. Badea, Y. Chen, M. Maggi and Y.-J. Lee, Agentic AI – Physicist Collaboration in Experimental Particle Physics: A Proof-of-Concept Measurement with LEP Open Data,2603.05735. 24

    work page arXiv

  13. [13]

    T. K. Aarrestad et al.,Building an AI-native Research Ecosystem for Experimental Particle Physics: A Community Vision,2602.17582

    work page arXiv

  14. [14]

    Gendreau-Distler, J

    E. Gendreau-Distler, J. Ho, D. Kim, L. T. Le Pottier, H. Wang and C. Yang,Automating High Energy Physics Data Analysis with LLM-Powered Agents, in39th Annual Conference on Neural Information Processing Systems: Includes Machine Learning and the Physical Sciences (ML4PS), 12, 2025.2512.07785

    work page arXiv 2025

  15. [15]

    Diefenbacher, A

    S. Diefenbacher, A. Hallin, G. Kasieczka, M. Krämer, A. Lauscher and T. Lukas,Agents of Discovery,2509.08535

    work page arXiv

  16. [16]

    Menzo, A

    T. Menzo, A. Roman, S. Gleyzer, K. Matchev, G. T. Fleming, S. Höche et al.,HEPTAPOD: Orchestrating High Energy Physics Workflows Towards Autonomous Agency,2512.15867

    work page arXiv

  17. [17]

    Hill and H

    J. Hill and H. J. Ryoo,GRACE: an Agentic AI for Particle Physics Experiment Design and Simulation, 1, 2026.2602.15039

    work page arXiv 2026

  18. [18]

    Esmail, A

    W. Esmail, A. Hammad and M. Nojiri,CoLLM: AI engineering toolbox for end-to-end deep learning in collider analyses,2602.06496

    work page arXiv

  19. [19]

    Y.-F. Lo, D. Kobylianskii and B. Nachman,An AI-based Detector Simulation and Reconstruction Model for the ALEPH Experiment at LEP,2604.11834

    work page internal anchor Pith review Pith/arXiv arXiv

  20. [20]

    Saito, T

    M. Saito, T. Kishimoto and J. Tanaka,Development of an LLM-Based System for Automatic Code Generation from HEP Publications, 4, 2026.2604.14696

    work page arXiv 2026

  21. [21]

    J. Birk, G. Kasieczka, S. Mishra-Sharma, B. Nachman, D. Noll and T. Wamorkar,A Scientific Human-Agent Reproduction Pipeline,2604.18752

    work page internal anchor Pith review Pith/arXiv arXiv

  22. [22]

    E. A. Moreno, S. Bright-Thonney, A. Novak, D. Garcia and P. Harris,AI Agents Can Already Autonomously Perform Experimental High Energy Physics,2603.20179

    work page arXiv

  23. [23]

    M. He, F. Jiang, J. Jiao, M. Li, K. Li, Y. Liao et al.,Dr.Sai: An agentic AI for real-world physics analysis at BESIII,2604.22541

    work page internal anchor Pith review Pith/arXiv arXiv

  24. [24]

    MadAgents

    T. Plehn, D. Schiller and N. Schmal,MadAgents,2601.21015

    work page internal anchor Pith review Pith/arXiv arXiv

  25. [25]

    Desai,amanmdesai/rooagent: 0.2.0,https://doi.org/10.5281/zenodo.20249499, May, 2026

    A. Desai,amanmdesai/rooagent: 0.2.0,https://doi.org/10.5281/zenodo.20249499, May, 2026. 10.5281/zenodo.20249499

    work page doi:10.5281/zenodo.20249499 2026

  26. [26]

    LangChain.ai Contributors,LangGraph: A low-level agent orchestration framework, https://github.com/langchain-ai/langgraph, 2024

    work page 2024

  27. [27]

    OpenAI et al.,GPT-4 Technical Report,2303.08774

    work page internal anchor Pith review Pith/arXiv arXiv

  28. [28]

    GitHub Copilot: AI-powered code assistance

    GitHub, “GitHub Copilot: AI-powered code assistance.” https://github.com/features/copilot, 2025

    work page 2025

  29. [29]

    Ollama Contributors,Ollama: A local large language model runtime,https://ollama.com, 2025

    work page 2025

  30. [30]

    Model context protocol

    “Model context protocol.”https://modelcontextprotocol.io, 2024

    work page 2024

  31. [31]

    Claude 3 model card

    Anthropic, “Claude 3 model card.”https://www.anthropic.com/claude, 2024

    work page 2024

  32. [32]

    Chase,LangChain: A modular framework for language model applications, https://github.com/langchain-ai/langchain, 2022

    H. Chase,LangChain: A modular framework for language model applications, https://github.com/langchain-ai/langchain, 2022. 25

    work page 2022

  33. [33]

    ChatOllama: Ollama model integration for LangChain

    LangChain Community, “ChatOllama: Ollama model integration for LangChain.” https://python.langchain.com/docs/integrations/providers/ollama, 2025

    work page 2025

  34. [34]

    McKinney,Data structures for statistical computing in Python, inProceedings of the 9th Python in Science Conference, pp

    W. McKinney,Data structures for statistical computing in Python, inProceedings of the 9th Python in Science Conference, pp. 56–61, 2010. DOI

    work page 2010

  35. [35]

    C. R. Harris et al.,Array programming with NumPy,Nature585(2020) 357–362, [2006.10256]

    work page internal anchor Pith review Pith/arXiv arXiv 2020

  36. [36]

    SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python

    P. Virtanen et al.,SciPy 1.0: Fundamental Algorithms for Scientific Computing in Python,Nature Meth.17(2020) 261–272, [1907.10121]

    work page internal anchor Pith review Pith/arXiv arXiv 2020

  37. [37]

    J. D. Hunter,Matplotlib: A 2d graphics environment,Computing in Science & Engineering9 (2007) 90–95

    work page 2007

  38. [38]

    DeepSeek-AI,DeepSeek-V3 Technical Report, 2024

    work page 2024

  39. [39]

    Lowin,FastMCP: A fast, pythonic way to build MCP servers and clients, https://github.com/jlowin/fastmcp, 2024

    J. Lowin,FastMCP: A fast, pythonic way to build MCP servers and clients, https://github.com/jlowin/fastmcp, 2024

    work page 2024

  40. [40]

    Piparo, P

    D. Piparo, P. Canal, E. Guiraud, X. Valls Pla, G. Ganis, G. Amadio et al.,RDataFrame: Easy Parallel ROOT Analysis at 100 Threads,EPJ Web Conf.214(2019) 06030

    work page 2019

  41. [41]

    The RooFit toolkit for data modeling

    W. Verkerke and D. P. Kirkby,The RooFit toolkit for data modeling,eConfC0303241(2003) MOLT007, [physics/0306116]

    work page internal anchor Pith review Pith/arXiv arXiv 2003

  42. [42]

    The automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations

    J. Alwall, R. Frederix, S. Frixione, V. Hirschi, F. Maltoni, O. Mattelaer et al.,The automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations,JHEP07(2014) 079, [1405.0301]. [44]PDF4LHC Working Groupcollaboration, R. D. Ball et al.,The PDF4LHC21 combination of global PDF fits...

    work page internal anchor Pith review Pith/arXiv arXiv 2014

  43. [43]

    LHAPDF6: parton density access in the LHC precision era

    A. Buckley, J. Ferrando, S. Lloyd, K. Nordström, B. Page, M. Rüfenacht et al.,LHAPDF6: parton density access in the LHC precision era,Eur. Phys. J. C75(2015) 132, [1412.7420]

    work page internal anchor Pith review Pith/arXiv arXiv 2015

  44. [44]

    A comprehensive guide to the physics and usage of PYTHIA 8.3

    C. Bierlich et al.,A comprehensive guide to the physics and usage of PYTHIA 8.3,SciPost Phys. Codeb.2022(2022) 8, [2203.11601]

    work page internal anchor Pith review Pith/arXiv arXiv 2022

  45. [45]

    FastJet user manual

    M. Cacciari, G. P. Salam and G. Soyez,FastJet User Manual,Eur. Phys. J. C72(2012) 1896, [1111.6097]

    work page internal anchor Pith review Pith/arXiv arXiv 2012

  46. [46]

    Confronting new physics theories to LHC data with MadAnalysis 5

    E. Conte and B. Fuks,Confronting new physics theories to LHC data with MADANALYSIS 5,Int. J. Mod. Phys. A33(2018) 1830027, [1808.00480]

    work page internal anchor Pith review Pith/arXiv arXiv 2018

  47. [47]

    The anti-k_t jet clustering algorithm

    M. Cacciari, G. P. Salam and G. Soyez,The anti-kt jet clustering algorithm,JHEP04(2008) 063, [0802.1189]

    work page internal anchor Pith review Pith/arXiv arXiv 2008

  48. [48]

    A standard format for Les Houches Event Files

    J. Alwall et al.,A Standard format for Les Houches event files,Comput. Phys. Commun.176 (2007) 300–304, [hep-ph/0609017]

    work page internal anchor Pith review Pith/arXiv arXiv 2007

  49. [49]

    Desai,LHEReader: Simplified Conversion from Les Houches Event Files to ROOT Format, 2603.01489

    A. Desai,LHEReader: Simplified Conversion from Les Houches Event Files to ROOT Format, 2603.01489

    work page arXiv

  50. [50]

    Behnke, K

    O. Behnke, K. Kröninger, T. Schörner-Sadenius and G. Schott, eds.,Data analysis in high energy physics: A practical guide to statistical methods. Wiley-VCH, Weinheim, Germany, 2013. 26

    work page 2013

  51. [51]

    Asymptotic formulae for likelihood-based tests of new physics

    G. Cowan, K. Cranmer, E. Gross and O. Vitells,Asymptotic formulae for likelihood-based tests of new physics,Eur. Phys. J. C71(2011) 1554, [1007.1727]. [54]ATLAScollaboration, G. Aad et al.,The ATLAS Experiment at the CERN Large Hadron Collider,JINST3(2008) S08003. [55]ATLAScollaboration,Review of the 13 TeV ATLAS Open Data release, . https://cds.cern.ch/r...

    work page internal anchor Pith review Pith/arXiv arXiv 2011

  52. [52]

    ATLAS open data

    ATLAS Collaboration, “ATLAS open data.”http://opendata.atlas.cern, 2020

    work page 2020

  53. [53]

    HEP Software Foundation Training: Analysis preservation and open data

    HSF Training Working Group, “HEP Software Foundation Training: Analysis preservation and open data.”https://hsf-training.github.io/hsf-training-matplotlib/, 2023. 27

    work page 2023