Clarify P64 source and memorization review limits

README.md

@@ -109,7 +109,7 @@ Three independent inference-only exports are available in the `research-selected
 | `p64-base-step200` | P64 trainer-selected best validation loss | Selected by training validation loss, not included in the cited completed step-680 downstream run. |
 | `p64-base-step680` | P64 completed final endpoint | Historical GraphWalks precision/recall and parse-zero F1 were zero with 100% format failure. |
 
-Each subfolder includes model shards, index, configuration, tokenizer and processor files; no optimizer, scheduler, RNG or resume shards. The exact file SHA-256 values and source binding are in [the selected export manifest](research-selected/MANIFEST.json). Tensor headers and indices were checked; no new GPU inference was performed during this publication. P64's original input manifest classifies the source as local-probe and does not establish production eligibility or strict long-dependency verification. The P456 and P64 exports are not interchangeable with the baseline variants above.
+Each subfolder includes model shards, index, configuration, tokenizer and processor files; no optimizer, scheduler, RNG or resume shards. The exact file SHA-256 values and source binding are in [the selected export manifest](research-selected/MANIFEST.json). Tensor headers and indices were checked; no new GPU inference was performed during this publication. P64's original input manifest classifies the source as local-probe and does not establish production eligibility or strict long-dependency verification. A scan of the P64 source data found security-related string hints, including names used in code examples; it did not establish whether those strings are valid credentials. Training-data source permissions have not been exhaustively resolved, and model memorization of sensitive material was not tested. The P456 and P64 exports are not interchangeable with the baseline variants above.
 
 For an individual model, download only its subfolder, for example: