diff options
| author | YurenHao0426 <Blackhao0426@gmail.com> | 2026-07-27 14:35:10 -0500 |
|---|---|---|
| committer | YurenHao0426 <Blackhao0426@gmail.com> | 2026-07-27 14:35:10 -0500 |
| commit | b90b5f43203fbafc4f1decb6adc11a76c813b2f1 (patch) | |
| tree | 4e2e4a42955e2f10dd6927bd2c8c01d52659a657 /RESNET_CROSSOVER.md | |
| parent | 129858078417fc5b7b6f5e219c607d7416930bd1 (diff) | |
experiment: lock crossover selector sources
Diffstat (limited to 'RESNET_CROSSOVER.md')
| -rw-r--r-- | RESNET_CROSSOVER.md | 7 |
1 files changed, 7 insertions, 0 deletions
diff --git a/RESNET_CROSSOVER.md b/RESNET_CROSSOVER.md index 28c8395..bcb9fad 100644 --- a/RESNET_CROSSOVER.md +++ b/RESNET_CROSSOVER.md @@ -102,6 +102,13 @@ before launch. A capped or failed cell is recorded and the shard continues. The complete analyzer rejects missing/duplicate cells, source or architecture drift, test evaluation, ordinary-example drift, and silent failure omission. +The R1 selector itself uses the same source discipline: one pre-launch lock +binds its complete 19-job registry to a clean commit, tracked-file hashes, and +the physical-GPU5/7 allowlist. Every job rechecks the lock before starting, +and its manifest records the resolved physical UUID. Formal launch occurs +from a detached worktree so unrelated main-branch commits cannot mix +revisions inside a shard. + ## R3 untouched confirmation No R3 test endpoint opens until all 27 R2 records and the complete analyzer |