Tootfinder

Efficiently Verifiable Proofs of Data Attribution
Ari Karchmer, Seth Neel, Martin Pawelczyk
https://arxiv.org/abs/2508.10866 https://arxiv.org/pdf/2508.108…

Efficiently Verifiable Proofs of Data Attribution
Data attribution methods aim to answer useful counterfactual questions like "what would a ML model's prediction be if it were trained on a different dataset?" However, estimation of data attribution models through techniques like empirical influence or "datamodeling" remains very computationally expensive. This causes a critical trust issue: if only a few computationally rich parties can obtain data attributions, how can resource-constrained parties trust that the provided attributions are inde…