# Beyond Sub-Gaussian Detector Scores: Robust Weighted Profile-Loss Change Point Detection for Human-LLM Text Segmentation

arXiv: https://arxiv.org/abs/2609.36888 · HTML: https://mlsanity.com/paper/2609.36888/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 26 references that are in the map.
- First posted on arXiv 29 Sep 2026.

## Builds on (most cited first, 18 of 18)

- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization](https://mlsanity.com/paper/1808.08745/) (2018)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature](https://mlsanity.com/paper/2301.11305/) (2023)
- [GLTR: Statistical Detection and Visualization of Generated Text](https://mlsanity.com/paper/1906.04043/) (2019)
- [Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvature](https://mlsanity.com/paper/2310.05130/) (2023)
- [Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text](https://mlsanity.com/paper/2401.12070/) (2024)
- [CoAuthor: Designing a Human-AI Collaborative Writing Dataset for Exploring Language Model Capabilities](https://mlsanity.com/paper/2201.06796/) (2022)
- [Intrinsic Dimension Estimation for Robust Detection of AI-Generated Texts](https://mlsanity.com/paper/2306.04723/) (2023)
- [Detecting AI-Generated Sentences in Human-AI Collaborative Hybrid Texts: Challenges, Strategies, and Insights](https://mlsanity.com/paper/2403.03506/) (2024)
- [Narrowest-Over-Threshold Detection of Multiple Change-points and Change-point-like Features](https://mlsanity.com/paper/1609.00293/) (2016)
- [Univariate Mean Change Point Detection: Penalization, CUSUM and Optimality](https://mlsanity.com/paper/1810.09498/) (2018)
- [Machine-Generated Text Localization](https://mlsanity.com/paper/2402.11744/) (2024)
- [Changepoint Detection in the Presence of Outliers](https://mlsanity.com/paper/1609.07363/) (2016)
- [A review on minimax rates in change point detection and localisation](https://mlsanity.com/paper/2011.01857/) (2020)
- [Adversarially robust change point detection](https://mlsanity.com/paper/2105.10417/) (2021)
- [Segmenting Human-LLM Co-authored Text via Change Point Detection](https://mlsanity.com/paper/2605.03723/) (2026)
- [Two-stage data segmentation permitting multiscale change points, heavy tails and dependence](https://mlsanity.com/paper/1910.12486/) (2019)

## Abstract (arXiv)

Mixed human-LLM documents require locating authorship transitions from detector scores whose reliability varies across text units. Existing weighted mean contrasts are vulnerable to extreme scores, while directly replacing means with robust centers obscures how a misplaced boundary changes the population objective. We propose Robust Weighted Profile-Loss Change Point Detection (RWCP), which combines capped reliability weights, Huber profile gains, and narrowest-over-threshold search in reliability coordinates. Our key analysis expresses the population gap between a true and a displaced split as a merge cost, avoiding a closed-form solution for the nonlinear center of a mixed segment. Under explicit curvature, spacing, and dependence conditions, core RWCP recovers the number of changes and localizes their boundaries; its quadratic-loss limit recovers squared weighted CUSUM. We also study RWCP-R, a separately evaluated decoder that shares source centers across nonadjacent passages. Across five retrospective cached-score benchmark families, core RWCP reduces family-macro WindowDiff by 17.6% relative to weighted change-point detection, and RWCP-R lowers it further. Boundary recovery improves most clearly for isolated changes, while both fixed configurations miss changes in collaborative and densely alternating text.