Declare a base model and correct the measured lineage

README.md

@@ -12,6 +12,7 @@ tags:
 - code-review
 - vulnerability-detection
 pipeline_tag: text-generation
+base_model: ApolloRaines/Sharona_Q27B-R_CodeSecurity_v2
 model-index:
 - name: Sharona_Q27B-R_CodeSecurity
   results:
@@ -29,6 +30,27 @@ model-index:
 
 # Sharona Q27B-R CodeSecurity
 
+> **Provenance correction -- measured, and the version numbers run backwards.**
+> This card previously declared no base model at all, so there was nothing for
+> a reader to diff against. Probing normalisation and bias survivors across
+> 355 shared tensors:
+>
+> | candidate | result |
+> |:----------|:-------|
+> | `Qwen/Qwen3.5-27B` | NOT the immediate parent -- 0/14 bit-identical, cos max 0.9983 |
+> | `ApolloRaines/Sharona_Q27B-R_CodeSecurity_v2` | BASE CONFIRMED -- 3/14 bit-identical |
+>
+> This artifact is derived FROM v2, so the name "v1" does not indicate the
+> earlier model. Qwen3.5-27B is a relative or ancestor rather than the parent.
+>
+> Margin, stated because it is thin: 3 of 14 survivors is exactly the minimum
+> our probe accepts. It clears the threshold by nothing, so read this as
+> "not a direct child of Qwen3.5-27B" -- which is firm -- rather than as v2
+> being settled against every other candidate, which it is not.
+>
+> Bit-identity on survivors also says NOTHING about method. Restricted
+> gradient training with frozen norms leaves this same signature.
+
 A [jBlaze](https://jblaze.dev) representation-engineered code security specialist. 27B parameters, GPTQ W4A16 quantized for efficient deployment.
 
 This model finds vulnerabilities in code. Command injection, SQL injection, XSS, deserialization attacks, OWASP Top 10 -- it catches what rushed reviews miss. It does not refuse to analyze attack patterns, because understanding how attacks work is how you stop them.