# New Provenance Tool Traces Which Training Records Belong to a Given Author

OriginBlame targets record- and token-level attribution in training data, aiming to build the forget set that machine-unlearning methods require.

- Published: 2026-07-17T05:29:37.841Z
- Canonical: https://polylog.news/ai/2026-07-17/new-provenance-tool-traces-which-training-records-belong-to
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [arXiv cs.AI](https://arxiv.org/abs/2607.13037)

A paper on arXiv introduces OriginBlame, a system for record- and token-level data provenance in AI training datasets, in the preprint. The authors frame it around a concrete gap: when a data contributor requests removal, unlearning algorit…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-07-17/new-provenance-tool-traces-which-training-records-belong-to (subscription information: https://polylog.news/pricing).