2026-10-11 18:01 UTC

model-provenance

band: coolmomentum: stable score: 0.002
temperature history

Episodes (3)

Independent replication will determine whether centered residual signatures reliably identify language-model training lineage across fine-tuning and common model transformations.
expiredknownscott: low
Independent evaluations will determine whether Model Genome can reliably distinguish scratch-trained LLMs from derived models and identify their training lineage.
expiredconvergesscott: medium
Reuters reportedly finds that a US government website used a Chinese AI search tool that the FBI said copied Anthropic, exposing a potential provenance-control gap in that public-sector deployment.
seedknownscott: low

Trajectory notes