# PINT: Probabilistic In-band Network Telemetry

arXiv: https://arxiv.org/abs/2007.03731 · HTML: https://mlsanity.com/paper/2007.03731/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jul 2020.

## Built on by (most cited first, 6 of 6)

- [QUIC-FL: Quick Unbiased Compression for Federated Learning](https://mlsanity.com/paper/2205.13341/) (2022)
- [Impact of RoCE Congestion Control Policies on Distributed Training of DNNs](https://mlsanity.com/paper/2207.10898/) (2022)
- [Automating In-Network Machine Learning](https://mlsanity.com/paper/2205.08824/) (2022)
- [GraphCC: A Practical Graph Learning-based Approach to Congestion Control in Datacenters](https://mlsanity.com/paper/2308.04905/) (2023)
- [NTP-INT: Network Traffic Prediction-Driven In-band Network Telemetry for High-load Switches](https://mlsanity.com/paper/2502.12834/) (2025)
- [Collaborative AI Agents and Critics for Fault Detection and Cause Analysis in Network Telemetry](https://mlsanity.com/paper/2604.00319/) (2026)

## Abstract (arXiv)

Commodity network devices support adding in-band telemetry measurements into data packets, enabling a wide range of applications, including network troubleshooting, congestion control, and path tracing. However, including such information on packets adds significant overhead that impacts both flow completion times and application-level performance. We introduce PINT, an in-band telemetry framework that bounds the amount of information added to each packet. PINT encodes the requested data on multiple packets, allowing per-packet overhead limits that can be as low as one bit. We analyze PINT and prove performance bounds, including cases when multiple queries are running simultaneously. PINT is implemented in P4 and can be deployed on network devices. Using real topologies and traffic characteristics, we show that PINT concurrently enables applications such as congestion control, path tracing, and computing tail latencies, using only sixteen bits per packet, with performance comparable to the state of the art.