TRAK

Description

Training-data attribution at scale via random-projection of gradients. Returns a per-training-example influence score on a target query.

Technical signature

in: (model, training_index, query) → out: { influence_scores[] }

Adversarial robustness

Requires gradient access; defeated when training index is unavailable.

Daubert eligibility

Method is peer-reviewed, has published error rates, and is reproducible from the chain-of-custody hash. Eligible for Tier-A admissibility packaging. Ultimate admissibility is the court's determination.