NUFORC Dramatic and Unusual UAP Sightings Classifier
Describe your sighting and see how dramatically it reads compared to 20,000+ real NUFORC reports.
What does "dramatic" and/or "unusual" mean?
It refers to language patterns, not whether your experience was real or significant.
NUFORC editors flag reports with dramatic and/or unusual vocabulary, vivid technical phrasing, or descriptions
that deviate from typical misidentification reports. A plain account of an extraordinary event
can still score low.
The model scores your description and these details together,
not the text alone. Shape, location, and time of night all move the
result, so every field is required. If you aren't sure of the shape,
Unknown is a real category the model was trained on,
pick it rather than guessing.
Your Score
—%
estimated chance of a "dramatic" flag
TypicalUnusual
Describe your sighting on the left and click Classify Sighting to see where your report ranks.
Score: — · — percentile · Threshold: —
Words in red pushed the score up.
Words in blue pushed it down.
Note. Held-out test set (n = 4,005). Confidence intervals from
5,000 bootstrap resamples, percentile method. Precision, recall,
specificity, and F1 are computed at the model's tuned decision threshold
of 0.17; ROC-AUC, average precision, and Brier score are
threshold-independent.