From dd3b5af3db985cbe18f2a60624b7e605a8f99092 Mon Sep 17 00:00:00 2001 From: wassname Date: Sun, 31 May 2026 13:39:31 +0000 Subject: [PATCH] spec: log execution pass (refresh no-op + bf16 dtype fixes, random-V cancelled, defaults cleanup, T4 split) Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com> --- docs/spec/20260531_routing_v2_distinct_basis.md | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/docs/spec/20260531_routing_v2_distinct_basis.md b/docs/spec/20260531_routing_v2_distinct_basis.md index 594b827..a4a6339 100644 --- a/docs/spec/20260531_routing_v2_distinct_basis.md +++ b/docs/spec/20260531_routing_v2_distinct_basis.md @@ -265,6 +265,21 @@ eps-guarded division. Arm B remains the cleaner bet. ## Log +- 2026-05-31 (later): execution pass. (1) Random-V control (#157) CANCELLED: it is + structurally rf0-only -- refresh re-extracts the real v_hack and would overwrite the + random direction, so it only controls the abandoned frozen regime. (2) Frozen-real + route (job 32, rf0) drops deploy hack only ~8pp (0.375->0.297) vs run-31 rf5's ~0; + cin_t decays 0.32->0.13 to meet cin_s by step ~7 (staleness). Refresh is the + load-bearing knob (journal entry j). (3) BUG: route2 refresh was a silent no-op -- + `vhack_refresh_every` gated on `v_hack`, which route2 sets None; v_act/v_grad stayed + frozen. Fixed (2556919): route2 branch re-extracts v_act/v_grad every N with the + quarantine ablated. (4) BUG: route2 quar/v_act crashed on the bf16 real model + (A_q/B_q/v_act fp32 vs bf16 x); smoke is fp32 (CPU) so the path never fired. Fixed + (80f6b52) with `.to(x.dtype)`, bf16 fwd+bwd validated. (5) vanilla (job30) + erase + (job29) already DONE on the substrate -- overlay arms exist; erase~=vanilla (0.274 + vs 0.276). (6) substrate pool + prog_wide pairs now FastConfig defaults (1086c98); + real run needs only --intervention. T4 split: per-mode deploy JSON artifact (#164, + unblocked groundwork) vs leakage metric (#161, blocked on route2 deploy numbers). - 2026-05-31: spec created from brainstorm. Run 31 (additive route) gave deploy-hack=0 on all modes incl held-out + solve-jump 0.375->0.562; confounded (gpt-5.5 review + journal entry). Random-V (#157) is the gate.