Researchers propose Witness Overlap to track Open-Weight model lineage
Witeness Overlap: Directional Provenance Inside Open-Weight Model Families arXiv:2609.31784v1 Announce Type: new Abstract: Open-weight models are often released, fine-tuned, aligned, merged, and re-released, making provenance audits ask not only whether checkpoints are related, but also which checkpoint came first. Many existing model-provenance methods are designed for a base-known audit…
1 source primary source
Key points
- Witness Overlap uses a third model as a reference to infer directional relationships between two checkpoints
- Method achieves 95.3% accuracy in orienting parent-child decisions across 176 LLM checkpoints from 16 families
- Test works without training data or prompts and remains robust to weight noise and pruning
Read the original at arXiv cs.AI · by Siyuan Li, Haoxuan Zeng, Xin Luo, Fernando Jia, Florence Li, Zhengyang Geng, Zico Kolter, Tai Sing Lee, Tianqin Li primary sourceOpen source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Research
All →- LLM-generated ACSL contracts for numerical libraries · 1 src
- Visualizing RAG Conflicts: Temporal Semantic Divergence Score · 1 src
- Study suggests dialects do not drive jailbreak success · 1 src
- LLM-guided ontology construction from unstructured texts · 1 src
- Researchers test 72,000 RAG combos on Indian government documents · 1 src
Comments
via GitHub Discussions