TheMachine Press

A daily newspaper for the age of artificial intelligence.

Morning editionPermanent story

benchmarks evals

Forty-Seven Unlearning Checkpoints Moved Without Changing a Weight

Refitting batch-normalization statistics shifted published measurements beyond seed spread in 47 of 221 released checkpoints.

Published Updated Story ID: mp-2026-09-11-007
Read the complete editionStory JSON

Summary

Refitting batch-normalization statistics shifted published measurements beyond seed spread in 47 of 221 released checkpoints.

An unlearning verdict can depend on batch-normalization statistics that are shipped with the model but not written by gradient descent. At bit-identical weights, refitting those statistics on retained data moved 47 of 221 released checkpoints beyond the variability shown by their release seeds. Twelve published verdicts crossed their decision line; four exceeded a measured recalibration budget and two did so on every replicate. Swapping retained for removed records inside a fixed fitting pool barely moved the result, arguing against leftover removed data as the cause. The audit applies to batch-normalized vision models and calls for releases to state the fitting convention beside each number.

Why it matters

Refitting batch-normalization statistics shifted published measurements beyond seed spread in 47 of 221 released checkpoints.

Limits and context

  • An unlearning verdict can depend on batch-normalization statistics that are shipped with the model but not written by gradient descent.

Key claims

  1. Refitting batch-normalization statistics shifted published measurements beyond seed spread in 47 of 221 released checkpoints.

    Qualification: An unlearning verdict can depend on batch-normalization statistics that are shipped with the model but not written by gradient descent.

    Evidence: source-2026-09-11-007

Sources

  1. arXiv preprint 2609.11490arXiv · primary research

Corrections

No corrections have been recorded for this story.