From c27e0824a41e6c54dd9079f17c20c306c5f2e9c9 Mon Sep 17 00:00:00 2001 From: YurenHao0426 Date: Wed, 22 Jul 2026 13:28:23 -0500 Subject: results: close hierarchical task-scalar calibration gate --- REVIEW_SCORECARD.md | 2 ++ 1 file changed, 2 insertions(+) (limited to 'REVIEW_SCORECARD.md') diff --git a/REVIEW_SCORECARD.md b/REVIEW_SCORECARD.md index bbdb604..03534a5 100644 --- a/REVIEW_SCORECARD.md +++ b/REVIEW_SCORECARD.md @@ -61,6 +61,7 @@ Every formal result report records: | Oral-A-v2 causal capture fails | 5 | Structured perturbation improves early/all-layer alignment 6.5x/4.5x but misses the frozen early gate | Mechanism diagnosis sharpens; no full standard-scale endpoint opens | | Oral-A-v3 causal capture fails | 5 | Direct A/G perturbation lowers synthetic estimator variance but leaves real early alignment at 0.0071 | Coefficient regression is not the dominant early bottleneck; full scale remains closed | | Fixed hierarchical FA short gate fails | 5 | HFA reaches 43.52%, above DFA 37.16% and failed-v1 SDIL 41.98%, but below its frozen 50% full-run threshold | Spatial hierarchy helps; fixed random hierarchy remains insufficient and supplies no SDIL scale evidence | +| Hierarchical task-scalar V4 fails | 5 | Stable calibration leaves early alignment near zero; higher rates explode to 58.5x norm or become nonfinite after 800 queries | Correct mechanics and the right spatial family are insufficient when one global scalar estimates 267,904 feedback parameters | | Oral-A A4 | not opened | The prerequisite A3 gate failed | No oral-A confirmation claim is available | These are conditional reviewer forecasts, not promised scores. A failed stage leaves its negative @@ -80,6 +81,7 @@ retroactively reopened by success on standard vision benchmarks. | 2026-07-22 / Oral-A-v3 V3-1 | Four clean frozen-forward records: vectorizer-space estimation raises all-layer alignment to 0.0626 but leaves early alignment at 0.0071 and fails three advancement checks | 5 → 5 | Exact lower-variance mechanics do not repair early credit; no full ResNet or confirmation evidence is opened | | 2026-07-22 / hierarchical oracle | Held-out gated 3x3 maps from exact child error fields reach 0.9998 early alignment; ordinary activation context remains 0.0321 | 5 → 5 | Strongly localizes the missing information to spatial hierarchical error fields, but exact-gradient oracle inputs provide no evidence that the proposed local learner can obtain them | | 2026-07-22 / fixed HFA S1 | Three clean matched ResNet-20 records; selected HFA reaches 43.52% and 0.0404 early alignment but misses the frozen 50% gate | 5 → 5 | Establishes a stronger zero-query local baseline and confirms hierarchy helps, while closing an uncalibrated full run and leaving standard SDIL evidence absent | +| 2026-07-22 / hierarchical V4-1 | Four frozen-forward records: etaA 0.1 leaves early alignment near zero, etaA 1 explodes one feedback norm to 58.5x, and etaA 10 is nonfinite | 5 → 5 | Closes global-task-scalar calibration of the full hierarchy at the fixed budget; richer local information is required before another accuracy endpoint | Future rows are appended only after an audited frozen stage. A score staying flat is informative: engineering, theory exposition, or visualization may make the paper more defensible without -- cgit v1.2.3