From c8bfa25f597dc2760855b3f71a59549753c9e4a2 Mon Sep 17 00:00:00 2001 From: YurenHao0426 Date: Thu, 23 Jul 2026 07:03:22 -0500 Subject: docs: record oral B recovery boundary --- PAPER_PLAN.md | 37 +++++++++++++++++++++---------------- 1 file changed, 21 insertions(+), 16 deletions(-) (limited to 'PAPER_PLAN.md') diff --git a/PAPER_PLAN.md b/PAPER_PLAN.md index 04f1d2f..290ac30 100644 --- a/PAPER_PLAN.md +++ b/PAPER_PLAN.md @@ -72,17 +72,16 @@ not imply that no-traffic scaling establishes the necessity of residualization. preservation, alignment, query/MAC/memory cost, and direct-versus-amortized causal feedback. 4. **Scientific negatives.** Broad top-down traffic, useful-depth learned - vectorization, the Harnett desired-velocity signature, and full standard - ResNet stability fail their frozen gates, defining the method's actual - boundary. + vectorization, the Harnett desired-velocity/full population signature, and + the original learned-vectorizer ResNet branch fail their frozen gates, + defining the method's actual boundary. 5. **Standard scale.** D3 passes all frozen checks at `91.18%` validation on - ResNet-20 versus BP's `91.62%`, but it is one seed. Do not promote this to - a robustness or depth-scaling claim until the already frozen paired - five-seed D4 confirmation and a separate depth panel pass. - The separate dynamic-depth recovery in `ORAL_A_RECOVERY.md` is the only - permitted depth panel: after oral-B passes, it reuses D4's ResNet-20 cells - and adds BP/DFA/clean-KP/dynamic ResNet-32/56 comparisons under a frozen - positive-depth-benefit and cost gate. + ResNet-20 versus BP's `91.62%`; the independent paired D4 panel then reaches + `91.584%` mean test accuracy versus clean KP's `91.388%`. This supports + ResNet-20 robustness, not a positive depth-scaling claim. The separately + frozen dynamic-depth panel in `ORAL_A_RECOVERY.md` was the only permitted + route to the latter, but its oral-B R2 prerequisite fails, so no new + ResNet-32/56 endpoint is opened. ## Figure order in the manuscript @@ -155,8 +154,10 @@ numbering. lesion; desired velocity is unsupported. - Keep the original failed screen intact. The separately frozen recovery factorizes learned causal role from within-episode performance innovation; - report it only if both its D4-gated development screen and untouched - 6-task-by-5-model confirmation pass. + its D4-gated development screen passes, but the untouched 6-task-by-5-model + confirmation fails the joint population-vectorization/longitudinal gate. + Report the learning, lesion, sign-inversion, and velocity positives as a + bounded diagnostic, not as a passed oral-B claim. - Even a complete recovery pass supports innovation-guided plasticity, not online neural control: the recovery fixes `kappa=0` by construction. @@ -177,7 +178,7 @@ numbering. | “Depth does not help this task.” | Claim says preservation; C2 reports the learned-vectorizer failure; Oral-A A3 is retained as a failed standard-scale test | Fatal to a broad scaling claim; the paper must remain mechanism-focused | | “Local methods hide enormous extra work.” | Logical queries, MACs, peak memory, wall time, C3 confirmation, EP/native protocols | Hardware implementations are not all equally optimized | | “Weak baselines define the win.” | BP/FA/DFA/direct NP/FF/PEPITA/EP plus native BurstCCN and Dual Prop | Native reproductions are one seed and method-native, not equal compute | -| “Harnett already proves the biological story.” | Original oral-B negative result plus the separately frozen role/velocity recovery and untouched 30-record confirmation | No biological claim changes unless the recovery passes; `kappa=0` cannot support desired velocity | +| “Harnett already proves the biological story.” | Original oral-B negative result plus the separately frozen role/velocity recovery and untouched 30-record confirmation | Recovery fixes learning and sign but fails the joint outcome/longitudinal gate; `kappa=0` cannot support desired velocity | | “The fast controller is just an unreported contrastive phase.” | Paired neutral observation count and elementwise/wall cost are explicit; no task-nudged state, loss query, or reverse pass is used | The instruction-off microphase is a real assumption and weakens the single-phase biological claim | | “The gates were selected after results.” | Git-frozen protocols, untouched confirmation seeds, failed branches retained | Early inherited pilots predate the strict boundary and must remain labeled | @@ -276,6 +277,10 @@ ResNet-20 with an inherited zero-query reciprocal credit path. The paper must still attribute reciprocal KP plasticity to prior work, count the paired neutral microphase and elementwise work, and retain the failed arbitrary-top-down, desired-velocity, online-control, and earlier unstable -branches. D4 alone cannot support positive added-depth utility. The next -paper-changing gate is oral-B R1/R2; only its separately frozen confirmation -can raise 7 to 8 and unlock the standard ResNet-20/32/56 oral-A panel. +branches. D4 alone cannot support positive added-depth utility. Oral-B R1 +selects `eta=0.1` with 98.05% worst-task development success, but the untouched +R2 confirmation fails the broader outcome-vectorization and longitudinal +signature checks despite 99.53% mean success and 30/30 positive sign +inversions. The score therefore remains 7 and the frozen +ResNet-20/32/56 oral-A panel stays closed. Do not repair thresholds or route +around the failed prerequisite. -- cgit v1.2.3