VESPER

Vetting Exoplanet Signals with Pixel-informed Evidence, Rapidly.

VESPER is a fast, learned vetter for transiting-planet candidates around TESS M dwarfs. Give it a star's TESS photometry and a candidate ephemeris (period, epoch, duration); it returns a calibrated probability that the signal is a planet, seven named impostor scores (background eclipsing binary, eclipsing binary, window alias, stellar rotation, companion dilution, no-signal, spacecraft systematics), and a keep/reject disposition — in about a tenth of a second per star, entirely offline (no external service calls). The frozen model, its full performance record and its known limitations are documented in the model card (VETTER_MODEL_CARD.md, shipped alongside this package).

Install

Python ≥ 3.10 required — check with python3 --version. Work in a fresh virtual environment (system Pythons are often older and their site-packages messy):

python3.11 -m venv vesper-env          # any Python >= 3.10
source vesper-env/bin/activate         # Windows: vesper-env\Scripts\activate
pip install torch --index-url https://download.pytorch.org/whl/cpu
pip install "tess-vesper[acquire]"

CPU-only torch is enough. The [acquire] extra adds lightkurve, used by vesper fetch to download and prepare TESS photometry for you. The package bundles the frozen model; installing it needs nothing else. The wheel bundles the frozen model (weights, calibrator, decision threshold, M-dwarf stellar catalog); their SHA-256 fingerprints are checked at every load.

How it works

1. You provide the ephemeris — VESPER judges a candidate at a given (period, T0, duration); it complements your transit search and your follow-up, taking the statistical-vetting step in between.
2. VESPER prepares its own photometry. From stitched, median-normalised PDCSAP flux before any detrending, it removes stellar variability with its own Gaussian-process model on a 200 s grid — the exact preparation the network was trained and certified on. vesper fetch builds that input for any TIC directly from the TESS archive; if you supply your own curves, give it pre-detrending flux and let VESPER do the rest.
3. It folds and judges. The signal is folded into shape views (global, transit zoom, secondary, odd/even, per-observing-block), normalised to the star's own noise, and weighed together with the stellar parameters and — when you have them — difference-image centroid measurements.
4. It answers in calibrated units. p_cal is a calibrated probability; the shipped threshold (0.29565…, calibrated to keep 95 % of planets) turns it into a disposition, and the named impostor heads tell you what the signal most resembles when it is not a planet.

Domain: TESS M dwarfs (Teff ≲ 4,000 K), periods ~0.5–100 d, cadences 20–200 s. Anything the contract cannot serve comes back as an explicit blocked:... status, never a silent skip.

Try it — the bundled example

Two well-known M-dwarf systems: L 98-59 (three small confirmed planets, plus one unconfirmed 1.05 d candidate signal — judge it yourself) and TOI-700 (four confirmed planets, including the habitable-zone TOI-700 d).

vesper example
vesper fetch --candidates candidates_example.csv --out-dir example_curves
vesper vet-batch --candidates candidates_example.csv --curves-dir example_curves --out example_results.csv

The fetch downloads every TESS sector of both stars (a few minutes). Then open example_results.csv: one row per candidate with p_cal, the named impostor scores and the disposition.

For your own targets, write the same kind of CSV — header tic_id, period_days, t0_btjd, duration_hours (optional: depth_ppm, planet_num) — and run the same two commands. Single candidates:

vesper vet --tic 307210830 --period 7.450726 --t0 1355.29 --duration-h 1.68 \
           --curves-dir example_curves

Reading the output

License and citation

MIT. The reference article is in preparation; until it is out, cite this package and its model card (VETTER_MODEL_CARD.md), which carries the full provenance of the frozen model.