summaryrefslogtreecommitdiff
path: root/RESNET_CROSSOVER.md
diff options
context:
space:
mode:
authorYurenHao0426 <Blackhao0426@gmail.com>2026-07-27 15:07:11 -0500
committerYurenHao0426 <Blackhao0426@gmail.com>2026-07-27 15:07:11 -0500
commit6af2ccbd5174c0832a11510dcb140fca206e7a38 (patch)
tree65ccc497924eb4509b18c57aad214f407ddb69cf /RESNET_CROSSOVER.md
parente39eda005e09c8c235afda34e92d4d69a73ff713 (diff)
experiment: make ResNet 27-cell R2 executable
Diffstat (limited to 'RESNET_CROSSOVER.md')
-rw-r--r--RESNET_CROSSOVER.md17
1 files changed, 17 insertions, 0 deletions
diff --git a/RESNET_CROSSOVER.md b/RESNET_CROSSOVER.md
index 126c051..ee1b28e 100644
--- a/RESNET_CROSSOVER.md
+++ b/RESNET_CROSSOVER.md
@@ -110,6 +110,23 @@ 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.
+The R2 executable contract is
+`experiments/resnet_crossover_r2.py`. It refuses any selector that is not the
+complete 19-record P1 pass, requires the selector itself to be committed,
+binds its hash and selected rates into a new clean-source launch lock, and
+materializes all 27 method--depth cells before sharding. The two shards
+interleave EP, Dual Propagation, and Forward--Forward rather than assigning all
+expensive state methods to one GPU.
+`experiments/analyze_resnet_crossover_r2.py` requires every manifest, retains
+timeout/nonfinite outcomes, rejects test access and
+source/split/architecture drift, and checks method-specific presentation,
+relaxation, local-VJP, and logical-query counts. The registry and schedule can
+be checked before P1 finishes with:
+
+```bash
+python experiments/resnet_crossover_r2_smoke.py
+```
+
## R3 untouched confirmation
No R3 test endpoint opens until all 27 R2 records and the complete analyzer