Record sealed ECP-7 deep decoder batch

[FatosLocos]

Summary

• add a deeper generic position-aware decoder with exactly one additional shared hidden layer
• preregister and execute sealed ECP7-B12-I on the complete Batch 10 training base
• record the valid negative result, integrity evidence, and exact artifact hashes
• retain Batch 10 as the strongest base and narrow ECP7-B13 to the symmetric sender-depth test

Result

The unchanged positive control remained at 100%. ECP7-B12-I regressed population train exactness to 71.53%, validation exactness to 47.98%, and translator validation exactness to 63.04%. Train, validation, translator, and injectivity all failed their registered gates, ruling out insufficient generic decoder depth as the Batch 10 bottleneck.

The confirmatory ECP-7 test split remains sealed.

Verification

• 82 passed
• ECP7-B12 configuration validates with split sizes 14336/1024/1024
• both sealed analyzers passed with 65/65 artifact hashes and no test metrics
• all eight hashes recorded in batch12-manifest.json match the local run artifacts