# Offline changepoint localization using a matrix of conformal p-values

arXiv: https://arxiv.org/abs/2505.00292 · HTML: https://mlsanity.com/paper/2505.00292/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 May 2025.

## Built on by (most cited first, 8 of 8)

- [E-valuator: Reliable Agent Verifiers with Sequential Hypothesis Testing](https://mlsanity.com/paper/2512.03109/) (2025)
- [Theoretical guarantees for change localization using conformal p-values](https://mlsanity.com/paper/2510.08749/) (2025)
- [Distribution-free changepoint localization after sequential change detection](https://mlsanity.com/paper/2606.01256/) (2026)
- [Distribution-free root cause analysis](https://mlsanity.com/paper/2605.21627/) (2026)
- [Conformal Changepoint Localization and Root Cause Analysis with Corrupted Observations](https://mlsanity.com/paper/2607.26481/) (2026)
- [ARC: Augmented-Rank Conformalization for Changepoint Localization --- Finite-Sample Validity and Distribution-Robust Efficiency](https://mlsanity.com/paper/2608.08424/) (2026)
- [Distribution-free inference on the number of changepoints](https://mlsanity.com/paper/2609.08234/) (2026)
- [Strategic Self-Consistency](https://mlsanity.com/paper/2609.30352/) (2026)

## Abstract (arXiv)

Changepoint localization is the problem of estimating the index at which a change occurred in the data generating distribution of an ordered list of data, or declaring that no change occurred. We present the broadly applicable MCP algorithm, which uses a matrix of conformal p-values to produce a confidence interval for a (single) changepoint under the mild assumption that the pre-change and post-change distributions are each exchangeable. We prove a novel conformal Neyman-Pearson lemma, motivating practical classifier-based choices for our conformal score function. Finally, we exemplify the MCP algorithm on a variety of synthetic and real-world datasets, including using black-box pre-trained classifiers to detect changes in sequences of images, text, and accelerometer data.