# Sure About That Line? Approaching Confidence-Based, Real-Time Line Assignment in Reading Gaze Data

arXiv: https://arxiv.org/abs/2605.00033 · HTML: https://mlsanity.com/paper/2605.00033/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 54 references that are in the map.
- First posted on arXiv 27 Apr 2026.

## Builds on (most cited first, 8 of 8)

- [SARA: Smart AI Reading Assistant for Reading Comprehension](https://mlsanity.com/paper/2404.06906/) (2024)
- [GenAIReading: Augmenting Human Cognition with Interactive Digital Textbooks Using Large Language Models and Image Generation Models](https://mlsanity.com/paper/2503.07463/) (2025)
- [Tracking the Progression of Reading Through Eye-gaze Measurements](https://mlsanity.com/paper/1905.02823/) (2019)
- [A Novel Slip-Kalman Filter to Track the Progression of Reading Through Eye-Gaze Measurements](https://mlsanity.com/paper/1907.07232/) (2019)
- [Dual input stream transformer for vertical drift correction in eye-tracking reading data](https://mlsanity.com/paper/2311.06095/) (2023)
- [Attention-driven read-aloud technology increases reading comprehension in children with reading disabilities](https://mlsanity.com/paper/2103.05296/) (2021)
- [GazeGenie: Enhancing Multi-Line Reading Research with an Innovative User-Friendly Tool](https://mlsanity.com/paper/2410.11873/) (2024)
- [Combining Automation and Expertise: A Semi-automated Approach to Correcting Eye Tracking Data in Reading Tasks](https://mlsanity.com/paper/2501.06977/) (2025)

## Abstract (arXiv)

Remote and webcam-based eye tracking in multi-line reading suffers from various noise factors and layout ambiguity, precisely where real-time reading support needs reliable, per-fixation line assignment. Prior work largely addresses this challenge post hoc or by restricting behavior (e.g., disallowing re-reading), undermining interactive use. We propose CONF-LA (Confidence-score-based Online Fixation-to-Line Assignment), a principled, low-latency approach that integrates knowledge about reading behavior and Gaussian line likelihoods over fixations to compute a posterior-line-score and defers assignments when uncertainty is high. Evaluated on existing open-source data, CONF-LA demonstrates stable performance in post hoc analysis and closes the online-offline gap (1-2 %) with a mean per-fixation latency of 0.348 ms. Our approach exhibits particular invariance toward regressions, yielding significant improvement in ad hoc median accuracies on children data (approx. 95 %) over all tested algorithms. We encourage further research in this direction and discuss possibilities for future development.