14–18 Sept 2026
Europe/Vienna timezone

Jet Taggers Rediscover the Energy Correlators: A Causal and Explainable-AI Dissection

16 Sept 2026, 16:50
20m

Speaker

Sanmay Ganguly (Indian Institute of Technology Kanpur (IN))

Description

We open the black box of machine-learning jet taggers, asking how they compute their decisions and whether they rediscover QCD. Applying the causal mechanistic-interpretability toolkit (ablation, path patching, logit-lens, probing) to a Particle Transformer top-tagger, we isolate a sparse six-head source -> relay -> readout circuit that recovers 97.3% of full-model AUC, encodes the energy-correlator basis over N-subjettiness, and implicitly factorizes top tagging into two-prong W→qq̄ identification. A complementary physics-informed explainability study on the Lund Jet plane, three explainers across LundNet, ParticleNet, and ParT, over 1-/2-/3-prong tagging and p_T bins shows explainer importance tracking the same substructure observables (τ₂₁, τ₃₂, C₂, C₃) across architectures, confirming that taggers learn genuine energy-correlator physics.

Authors

Ms Pahal Patel (Indian Institute of Technology, Kanpur) Sanmay Ganguly (Indian Institute of Technology Kanpur (IN)) Mr Saurabh Rai (Indian Institute of Technology, Kanpur)

Presentation materials

There are no materials yet.