Evidence record 18283 · automatically gathered

Can Webcam Gaze Constrain Mesa-Objectives in Driving Models? An Instrument Precision Analysis

Current hazard detection systems in autonomous driving may develop mesa objectives, learned internal goals that achieve high training performance through spurious correlations rather than genuine hazard recognition. We investigate whether human gaze patterns, captured via webcam-based eye tracking (WebGazer.js), can serve as privileged information to constrain mesa-objective formation. We collected 137,663 frame-level gaze samples synchronized with hazard annotations across 388 real dashcam clip

Record details

Published: 9 August 2026
Source: arXiv cs.HC
Category: Research
Topics: Privacy · Finance, VC & PE
Retrieved: 11 August 2026

source-onlyevidence status

These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.

How to cite this record

ethics.ai (9 August 2026), “Can Webcam Gaze Constrain Mesa-Objectives in Driving Models? An Instrument Precision Analysis,” evidence record 18283, https://ethics.ai/record/18283 (originally published by arXiv cs.HC).

JSON

Use and limitations

This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.