# Jolt Atlas: Verifiable Inference via Lookup Arguments in Zero Knowledge

arXiv: https://arxiv.org/abs/2602.17452 · HTML: https://mlsanity.com/paper/2602.17452/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 21 references that are in the map.
- First posted on arXiv 19 Feb 2026.

## Builds on (most cited first, 2 of 2)

- [TeleSparse: Practical Privacy-Preserving Verification of Deep Neural Networks](https://mlsanity.com/paper/2504.19274/) (2025)
- [Bionetta: Efficient Client-Side Zero-Knowledge Machine Learning Proving](https://mlsanity.com/paper/2510.06784/) (2025)

## Built on by (most cited first, 3 of 3)

- [Crypto x AI, AI x Crypto: A Survey](https://mlsanity.com/paper/2606.13892/) (2026)
- [ZK-SR117: A Chunked Zero-Knowledge Attestation Design for Aggregated Fair-Lending Metrics, with a Control Mapping toward Full SR 11-7 Coverage](https://mlsanity.com/paper/2608.02664/) (2026)
- [Maverick: Private and Verifiable LLM Inference Made Practical via Matrix-Vector Multiplication Delegation](https://mlsanity.com/paper/2609.10264/) (2026)

## Abstract (arXiv)

We present Jolt Atlas, a zero-knowledge machine learning (zkML) framework that extends the Jolt proving system to model inference. Unlike zkVMs (zero-knowledge virtual machines), which emulate CPU instruction execution, Jolt Atlas adapts Jolt's lookup-centric approach and applies it directly to ONNX tensor operations. The ONNX computational model eliminates the need for CPU registers and simplifies memory consistency verification. In addition, ONNX is an open-source, portable format, which makes it easy to share and deploy models across different frameworks, hardware platforms, and runtime environments without requiring framework-specific conversions. Our lookup arguments, which use sumcheck protocol, are well-suited for non-linear functions -- key building blocks in modern ML. We apply optimisations such as neural teleportation to reduce the size of lookup tables while preserving model accuracy, as well as several tensor-level verification optimisations detailed in this paper. We demonstrate that Jolt Atlas can prove model inference in memory-constrained environments -- a prover property commonly referred to as textitstreaming. Furthermore, we discuss how Jolt Atlas achieves zero-knowledge through the BlindFold technique, as introduced in Vega. In contrast to existing zkML frameworks, we show practical proving times for classification, embedding, automated reasoning, and small language models. Jolt Atlas enables cryptographic verification that can be run on-device, without specialised hardware. The resulting proofs are succinctly verifiable. This makes Jolt Atlas well-suited for privacy-centric and adversarial environments. In a companion work, we outline various use cases of Jolt Atlas, including how it serves as guardrails in agentic commerce and for trustless AI context (often referred to as textitAI memory).