research
A Transit Classifier Meets the Blend Ceiling
A TESS classifier's ROC area fell from 0.97 to 0.50 against real rejected candidates; a multi-stage pipeline then independently validated TOI-6662 b.
Summary
A TESS classifier's ROC area fell from 0.97 to 0.50 against real rejected candidates; a multi-stage pipeline then independently validated TOI-6662 b.
Blended eclipses made 42 percent of 145 examined false positives and capped what one light curve could reveal. The pipeline added centroid, scene and Gaia evidence before validating a 0.94-Earth-radius planet on a 7.05-hour orbit.
Why it matters
A TESS classifier's ROC area fell from 0.97 to 0.50 against real rejected candidates; a multi-stage pipeline then independently validated TOI-6662 b.
Limits and context
No additional limitation was separately recorded.
Key claims
A TESS classifier's ROC area fell from 0.97 to 0.50 against real rejected candidates; a multi-stage pipeline then independently validated TOI-6662 b.
Evidence: source-2026-11-02-021
Sources
- arXiv preprint 2610.42009, original v1arXiv · primary research
Corrections
No corrections have been recorded for this story.