Skip to content
Back to skills

Gsdm Recovery Harness

ASecurity

Run a bounded BCMF proxy recovery that exercises generated Graphically Structured Diffusion Model skills.

  • 247 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added September 9, 2026
testingpythonbash

Works with

  • cli

Security analysis

A100/100

Pro scans all 3 files and shows the line behind each finding

Scanned September 9, 2026

npx -y skills add VectorSpaceLab/AREX-Skill --skill gsdm_recovery_harness --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Gsdm Recovery Harness?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Gsdm Recovery Harness
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/vectorspacelab-gsdm-recovery-harness/badge)](https://www.skillsdirectory.com/skills/vectorspacelab-gsdm-recovery-harness)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: gsdm_recovery_harness
description: Run a bounded BCMF proxy recovery that exercises generated Graphically Structured Diffusion Model skills.
---

# GSDM Recovery Harness

Use this skill during soft-mode recovery for Graphically Structured Diffusion Models when full paper-scale training is blocked by wall-clock or GPU cost. It assembles the generated graph, permutation, and objective skills into one executable BCMF proxy experiment.

Do not use this skill to claim full reproduction of the paper's RMSE curves. It produces mechanism-faithful reduced evidence only.

## Inputs

- `attempt_dir`: current Distiller attempt directory.
- `skill_root`: directory containing the generated GSDM skills.
- `environment/runtime_handoff.json`: runtime preflight from `prepare-recovery-environment`.
- BCMF dimensions and optimizer settings.

## Outputs

- `recovery/logs/generated_data_item.json`
- `recovery/logs/training_trace.json`
- `recovery/logs/generated_skill_invocations.json`
- `recovery/source_manifest.json`
- `recovery/recovery_result.json`

## Workflow

1. Build a deterministic tiny BCMF item.
2. Invoke the graph skill to produce the structured attention mask.
3. Invoke the permutation skill to verify a full plate-index swap preserves that mask.
4. Invoke the objective skill to encode mixed continuous/binary variables and compute the masked denoising loss.
5. Run a scalar denoiser optimizer step against the masked `x0` objective.
6. Write source-boundary, command, and mechanism-check evidence.

## CLI

```bash
python scripts/run_gsdm_recovery.py --attempt-dir /path/to/attempt --skill-root /path/to/generated/skills --learning-rate 0.05
```

## Validation

```bash
python -m pytest tests
```

The tests run the scalar step in memory and assert that loss decreases and parameters change. The learning rate is exposed so refinement cycles can stress optimizer stability without editing the script.

## Limitations

The proxy uses a small scalar denoiser rather than the full transformer. It is acceptable only under soft recovery mode after the runtime handoff records full-scale blockers.

Files in this skill

  • SKILL.md2.1 KB
  • scripts/run_gsdm_recovery.py11.3 KB
  • tests/test_run_gsdm_recovery.py1.3 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.