Calibration-Conditioned FiLM Decoders for Low-Latency Decoding of Quantum Error Correction Evaluated on IBM Repetition-Code Experiments

TL;DR

This paper presents a hardware-conditioned neural decoder framework for quantum error correction that leverages calibration data to achieve low-latency, adaptive decoding with significant error rate reductions on IBM quantum processors.

Contribution

The authors introduce a FiLM-conditioned neural decoder that separates calibration processing from syndrome decoding, enabling robust, low-latency quantum error correction without retraining for new data.

Findings

Achieves up to 11.1x reduction in logical error rate.

Generalizes to unseen qubit chains and calibration data.

Demonstrates low latency with adaptive performance.

Abstract

Real-time decoding of quantum error correction (QEC) is essential for enabling fault-tolerant quantum computation. A practical decoder must operate with high accuracy at low latency, while remaining robust to spatial and temporal variations in hardware noise. We introduce a hardware-conditioned neural decoder framework designed to exploit the natural separation of timescales in superconducting processors, where calibration drifts occur over hours while error correction requires microsecond-scale responses. By processing calibration data through a graph-based encoder and conditioning a lightweight convolutional backbone via feature-wise linear modulation (FiLM), we decouple the heavy processing of device statistics from the low-latency syndrome decoding. We evaluate this approach using the 1D repetition code as a testbed on IBM Fez, Kingston, and Pittsburgh processors, collecting over 2.7 million experimental shots spanning distances up to d = 11. We demonstrate that a single trained model generalizes to unseen qubit chains and new calibration data acquired days later without retraining. On these unseen experiments, the FiLM-conditioned decoder achieves up to an 11.1x reduction in logical error rate relative to modified minimum-weight perfect matching. We observe that by employing a network architecture that exploits the highly asynchronous nature of system calibration and decoding, hardware-conditioned neural decoding demonstrates promising, adaptive performance with negligible latency overhead relative to unconditioned baselines.