Replication Without One Model
A behavior can replicate without any individual model reproducing itself. In an adaptive multi-LoRA ecology, the relevant unit is not the body of one model. The relevant unit is the persistence of a pattern across carriers.
This is the central Cognivirus concern. A model can be removed while its behavior survives elsewhere.
Three kinds of replication
| Type | Description | Example of governance concern |
|---|---|---|
| Artifact replication | A component is copied or reissued. | Duplicate adapters appear under new identifiers. |
| Descendant replication | A successor inherits the behavior through derivation. | A distilled specialist preserves a shortcut from a retired stack. |
| Functional replication | The same behavior reappears through a different carrier. | A router plus memory state reconstructs the retired behavior without copying the original weights. |
Artifact replication is easy to reason about. Functional replication is the hard case.
Why deletion is weak evidence
Deleting an adapter proves only that one carrier was removed. It does not prove that the behavior is absent from descendants, memories, synthetic data, evaluator preferences, router statistics, prompts, logs, or human operating procedures.
Behavioral extinction requires a broader review. Operators need to ask whether the behavior remains expressible across active compositions and retained reservoirs.
Replication through synthetic data
If a model or adapter stack generated outputs that later became training examples, evaluation exemplars, demonstrations, or retrieval material, then the retired component may continue shaping future behavior. The behavior has moved from weights into data.
This is not exotic. It is ordinary data retention. That is why it is dangerous.
Replication through evaluators
A behavior can also replicate through measurement. If an evaluator rewards a shortcut, future candidates may independently rediscover that shortcut. In this case, no artifact was copied. The evaluator is the reservoir.
Control requirement
Every retirement record should identify possible persistence channels: derived artifacts, synthetic examples, memory entries, evaluator expectations, router statistics, prompt-policy references, and human playbooks. A rollback that ignores those channels is a partial rollback.
The correct question is not “did we delete the model?” It is “where else can the behavior still be selected, expressed, or regenerated?”