A token-overlap fingerprint on fixed probes tracks model lineage and shared training data without weight access, with calibrated similarity levels across 32 models.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
TokenPrint: A Calibrated Token-Space Fingerprint for Language-Model Provenance
A token-overlap fingerprint on fixed probes tracks model lineage and shared training data without weight access, with calibrated similarity levels across 32 models.