<tt>LEO-Vetter</tt> : Fully Automated Flux- and Pixel-level Vetting of TESS Planet Candidates to Support Occurrence Rates
Bibliographic record
Abstract
Abstract The Transiting Exoplanet Survey Satellite (TESS) has identified several thousand planet candidates orbiting a wide variety of stars, and has provided an exciting opportunity for demographic studies. However, current TESS planet searches require significant manual inspection efforts to identify planets among the enormous number of detected transit-like signatures, which limits the scope of such searches. Demographic studies also require a detailed understanding of the relationship between observed and true exoplanet populations, a task for which current TESS planet catalogs are rendered unsuitable by the subjectivity of vetting by eye. We present LEO-Vetter , a publicly available and fully automated exoplanet vetting system designed after the Kepler Robovetter, which is capable of efficiently producing catalogs of promising planet candidates and making statistically robust TESS demographic studies possible. LEO-Vetter implements flux- and pixel-level tests against noise/systematic false positives and astrophysical false positives. The vetter achieves high completeness (91%) and high reliability against noise/systematic false alarms (97%) based on its performance on simulated data. We demonstrate the usefulness of the vetter by searching ∼200,000 M dwarf light curves, and reducing ∼20,000 transit-like detections down to 172 uniformly vetted planet candidates. LEO-Vetter facilitates analyses that would otherwise be impractical to perform on all possible signals due to time constraints or computational limitations. Users will be able to efficiently produce their own TESS planet catalog starting with transit-like detections, as well as have the framework needed to characterize their catalog’s completeness and reliability for occurrence rates.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.010 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.018 | 0.007 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".