Witness Overlap: Directional Provenance Inside Open-Weight Model Families

The paper introduces Witness Overlap, a new method for determining directional provenance among open-weight model checkpoints. By using a third same-family checkpoint as a witness, the technique compares local geometry to infer which checkpoint is the parent of another, achieving 95.3% accuracy on 176 LLM checkpoints from 16 families. The authors also demonstrate robustness to weight noise and pruning, and extend the approach to VLM and diffusion families.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms
• diffusion
• fine-tuning
• efficiency
• multimodal