brainstorming
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).
Explorer les Skills
Développement · SKILL.md
sar_sharpness_aware_update
sar_sharpness_aware_updateUse this skill when implementing the SAM-like sharpness-aware two-step update used by SAR recovery experiments.
Independent GitHub snapshot · Automated classification · Original documentation governs
Documentation de la Skill
GitHubname: sar_sharpness_aware_update description: Use this skill when implementing the SAM-like sharpness-aware two-step update used by SAR recovery experiments.
Sharpness-Aware Update
When To Use
Use this skill for SAR stable test-time adaptation work that needs: Run a two-step SAM-style update around reliable entropy minimization. Do not use it as a generic ImageNet-C runner or as permission to read the original SAR repository during recovery.
Inputs
- trainable parameters, gradients or differentiable proxy model, reliable samples
Outputs
- perturbation norm, first-step parameters, second-step updated parameters, loss trace
Workflow
- Read the caller-provided stream, logits, parameter metadata, or entropy trace.
- Apply the SAR-specific invariant documented in this skill: SAR optimizes both entropy and entropy sharpness by minimizing entropy after an adversarial weight perturbation.
- Produce structured numeric evidence for recovery logs.
- Keep proxy/reduced results explicitly labeled when the full ImageNet-C runtime is unavailable.
Validation
Run python scripts/sharpness_aware_update.py when the script has a CLI, then run python -m pytest tests or the Distiller skill validator with --run-tests.
Limitations
This skill captures a reusable SAR mechanism. It does not contain pretrained weights, ImageNet-C data, or original repository code, and it should be combined with other SAR skills for end-to-end recovery.