Weight-space spectral statistics and subspace geometry separate independent, same-family, and shared-base LLMs, and track fine-grained post-training differences.
We distinguish two subcategories based on fine-grained variation sources
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Who Built This Model? Tracing LLM Lineage via Spectral Fingerprints in Weight Space
Weight-space spectral statistics and subspace geometry separate independent, same-family, and shared-base LLMs, and track fine-grained post-training differences.