An AI-guided TESS search flagged a planet candidate around G 249-11
Source check: Source checked. Not independent scientific confirmation.
Finding: An agent-guided search of archived TESS observations found repeating dips around the nearby red dwarf G 249-11 at a period of about 5.31 days. An ephemeris fitted to two sectors predicted dips in two held-out sectors. If the signal comes from a planet, its fitted radius is about 1.6 times Earth’s.
Technology: Claude Sonnet 5.5; Infinity Machine research agent
Family Claude: profile · models page
Publication: Preprint · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- Claude Sonnet 5.5 proposed and executed a box-least-squares search of TESS light curves. The author applied photometric, catalogue and held-out timing checks.
- Test and result
- The author used two sectors for initial fitting and two other existing sectors for a timing check. A combined false-alarm probability of about 0.002 was estimated from 400 end-to-end null realizations.
- Limitation / still unknown
- A bound eclipsing companion and a nearby faint source remain plausible alternatives. The candidate is unconfirmed; the held-out data came from existing observations.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://zenodo.org/api/records/23651677 · https://arxiv.org/html/2610.35579v1
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review date: 21 Nov 2026. Review scope: Zenodo v1 author research note record; Infinity Machine §3.6 and Appendix A.10 source and held-out test.
No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.
Editorial assessment: Impact 2/5 · Validation 2/5 · Novelty 2/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.