Record ECP-7 Batch 19 bounded replay pulse

[FatosLocos]

Summary

• add a preregistered linear decay for global collision-replay weight
• run sealed seed-11 positive-control and intervention development arms
• record the valid negative result and compact artifact hashes
• update the fresh-agent guide with the justified Batch 20 direction

Result

The bounded replay pulse reached 83.74% train exactness, 82.04% mean validation, a new-best 80.57% worst-link validation, and 83.50% universal-translator validation. Validation and translator gates pass, but train thresholds and sender injectivity fail. The ECP-7 confirmatory split remains sealed.

Verification

• 105 passed
• configuration and schemas valid: 14336/1024/1024
• both post-hoc analyses match 65 artifact hashes
• 16,384 validation-only episodes per arm
• no confirmatory-test metrics
• all messages use valid local alphabets and exactly 14 declared bits