arXiv subjects

Pratik Jawahar

Publications and source records attributed to Pratik Jawahar.

10 recordsLinked to original sources

arXiv2026

FactoryNet: A Large-Scale Dataset toward Industrial Time-Series Foundation Models

Industrial machines are actuated systems, yet most open time-series corpora record sensor outcomes alone; the few that do log commanded signals expose them in vendor-specific forms that differ from machine to machine, so commanded intent and measured response cannot be compared across embodiments. We introduce FactoryNet, a pretraining corpus for industrial time-series: 113M datapoints across 57k end-to-end task executions (15k real, 42k synthetic) on seven embodiments and four tasks, with 27 annotated anomaly types alongside healthy baselines and counterfactual pairs. Every signal in every source is mapped into a single control-theoretic schema, Setpoint, Effort, Feedback, Context (S-E-F-C), which expresses any actuated system in a common representational frame and makes commanded-versus-realized dynamics readable as explicit prediction residuals. Using the corpus, we find that a task-phase model trained on simulation, with no real phase labels, recovers roughly two thirds of the real-data ceiling on both robots, and that transfer holds within a robot family but rarely across manufacturers. Fault signatures behave differently: an uncalibrated simulator gives no detectable fault signal on either robot, and aligning the feature distributions does not repair it. What separation there is comes from Effort: motor current distinguishes faults where measured tool motion is close to chance, and calibrating the simulator to reproduce that one channel recovers a payload fault on the real robot. We read this as simulation capturing the stable structure of a task while fault behaviour stays diverse and fault-type specific. We release FactoryNet as a growing, multi-embodiment substrate for industrial foundation models.

cs.LG↗

arXiv2026

KITE: A Knowledge-Injected Temporal Encoder for Time-Series Event Forecasting

Forecasting rare, high-cost events in multivariate time-series systems is hard because their precursors are seldom observed, so a purely data-driven model has little to learn from. The engineers who run these systems, however, hold knowledge that precedes such events, information absent from the scarce labels. We call this a semantic prior and inject it into a self-supervised event forecaster through two switchable mechanisms, a covariate mechanism and an attention-bias mechanism, each the identity at its null, so one architecture serves every prior type with no per-dataset architecture search. A prior helps when it supplies information the observed window does not already contain: in a short context an informative prior beats no prior in-domain (pooled h-AUROC over the no-prior baseline: a periodicity clock +14%, p<0.001; a conservation residual +47% at a 0.25 label fraction), and a working prior transfers out-of-domain (+53%), substituting for feature transfer, while priors the window already recovers stay inert and the attention-bias mechanism shows no measurable gain. KITE is a switchable, attributable route to contextual conditioning, and a substrate for scaling toward cross-domain, pretrained time-series foundation world models that carry their governing structure explicitly.

cs.LG↗

arXiv2026

CHLU: The Causal Hamiltonian Learning Unit as a Symplectic Primitive for Deep Learning

Current deep learning primitives dealing with temporal dynamics suffer from a fundamental dichotomy: they are either discrete and unstable (LSTMs) \citep{pascanu_difficulty_2013}, leading to exploding or vanishing gradients; or they are continuous and dissipative (Neural ODEs) \citep{dupont_augmented_2019}, which destroy information over time to ensure stability. We propose the \textbf{Causal Hamiltonian Learning Unit} (pronounced: \textit{clue}), a novel Physics-grounded computational learning primitive. By enforcing a Relativistic Hamiltonian structure and utilizing symplectic integration, a CHLU strictly conserves phase-space volume, as an attempt to solve the memory-stability trade-off. We show that the CHLU is designed for infinite-horizon stability, as well as controllable noise filtering. We then demonstrate a CHLU's generative ability using the MNIST dataset as a proof-of-principle.

cs.LG↗

arXiv2026

SMARTHEP: training PhD students in real-time analysis at the LHC and in industry

In this invited Editorial for Software and Computing for Big Science, we describe the SMARTHEP Innovative Training Network funded via the Marie Skłodowska-Curie Actions between 2021 and 2025. SMARTHEP trained 12 PhD students to advance machine learning and real-time analysis in high-energy physics experiments and industrial applications. We present the perspective of students, supervisors, and external observers of the network, concerning the work done within the network, the added value compared to ``typical'' PhD positions, and the emerging themes and directions from our experiences in the past four years.

physics.ed-ph↗

arXiv2025

Knowledge is Overrated: A zero-knowledge machine learning and cryptographic hashing-based framework for verifiable, low latency inference at the LHC

Low latency event-selection (trigger) algorithms are essential components of Large Hadron Collider (LHC) operation. Modern machine learning (ML) models have shown great offline performance as classifiers and could improve trigger performance, thereby improving downstream physics analyses. However, inference on such large models does not satisfy the $40\text{MHz}$ online latency constraint at the LHC. In this work, we propose \texttt{PHAZE}, a novel framework built on cryptographic techniques like hashing and zero-knowledge machine learning (zkML) to achieve low latency inference, via a certifiable, early-exit mechanism from an arbitrarily large baseline model. We lay the foundations for such a framework to achieve nanosecond-order latency and discuss its inherent advantages, such as built-in anomaly detection, within the scope of LHC triggers, as well as its potential to enable a dynamic low-level trigger in the future.

hep-ex↗

arXiv2025

Review of Machine Learning for Real-Time Analysis at the Large Hadron Collider experiments ALICE, ATLAS, CMS and LHCb

The field of high energy physics (HEP) has seen a marked increase in the use of machine learning (ML) techniques in recent years. The proliferation of applications has revolutionised many aspects of the data processing pipeline at collider experiments including the Large Hadron Collider (LHC). In this whitepaper, we discuss the increasingly crucial role that ML plays in real-time analysis (RTA) at the LHC, namely in the context of the unique challenges posed by the trigger systems of the large LHC experiments. We describe a small selection of the ML applications in use at the large LHC experiments to demonstrate the breadth of use-cases. We continue by emphasising the importance of collaboration and engagement between the HEP community and industry, highlighting commonalities and synergies between the two. The mutual benefits are showcased in several interdisciplinary examples of RTA from industrial contexts. This whitepaper, compiled by the SMARTHEP network, does not provide an exhaustive review of ML at the LHC but rather offers a high-level overview of specific real-time use cases.

hep-ex↗

arXiv2024

Baler -- Machine Learning Based Compression of Scientific Data

Storing and sharing increasingly large datasets is a challenge across scientific research and industry. In this paper, we document the development and applications of Baler - a Machine Learning based data compression tool for use across scientific disciplines and industry. Here, we present Baler's performance for the compression of High Energy Physics (HEP) data, as well as its application to Computational Fluid Dynamics (CFD) toy data as a proof-of-principle. We also present suggestions for cross-disciplinary guidelines to enable feasibility studies for machine learning based compression for scientific data.

physics.comp-ph↗

arXiv2024

The SMARTHEP European Training Network

Synergies between MAchine learning, Real-Time analysis and Hybrid architectures for efficient Event Processing and decision-making (SMARTHEP) is a European Training Network, training a new generation of Early Stage Researchers (ESRs) to advance real-time decision-making, driving data-collection and analysis towards synonymity. SMARTHEP brings together scientists from major LHC collaborations at the frontiers of real-time analysis (RTA) and key specialists from computer science and industry. By solving concrete problems as a community, SMARTHEP will further the adoption of RTA techniques, enabling future High Energy Physics (HEP) discoveries and generating impact in industry. ESRs will contribute to European growth, leveraging their hands-on experience in machine learning and accelerators towards commercial deliverables in fields that can profit most from RTA, e.g., transport, manufacturing, and finance. This contribution presents the training and outreach plan for the network, and is intended as an opportunity for further collaboration and feedback from the CHEP community.

hep-ex↗

arXiv2023

Applications of Deep Learning to physics workflows

Modern large-scale physics experiments create datasets with sizes and streaming rates that can exceed those from industry leaders such as Google Cloud and Netflix. Fully processing these datasets requires both sufficient compute power and efficient workflows. Recent advances in Machine Learning (ML) and Artificial Intelligence (AI) can either improve or replace existing domain-specific algorithms to increase workflow efficiency. Not only can these algorithms improve the physics performance of current algorithms, but they can often be executed more quickly, especially when run on coprocessors such as GPUs or FPGAs. In the winter of 2023, MIT hosted the Accelerating Physics with ML at MIT workshop, which brought together researchers from gravitational-wave physics, multi-messenger astrophysics, and particle physics to discuss and share current efforts to integrate ML tools into their workflows. The following white paper highlights examples of algorithms and computing frameworks discussed during this workshop and summarizes the expected computing needs for the immediate future of the involved fields.

hep-ex↗

arXiv2021

Improving Variational Autoencoders for New Physics Detection at the LHC with Normalizing Flows

We investigate how to improve new physics detection strategies exploiting variational autoencoders and normalizing flows for anomaly detection at the Large Hadron Collider. As a working example, we consider the DarkMachines challenge dataset. We show how different design choices (e.g., event representations, anomaly score definitions, network architectures) affect the result on specific benchmark new physics models. Once a baseline is established, we discuss how to improve the anomaly detection accuracy by exploiting normalizing flow layers in the latent space of the variational autoencoder.

hep-ph↗