Skip to content
Back to skills

Output Label Mapping

ASecurity

Convert frozen source-model logits or predictions to target classes with AutoVP label mapping strategies.

  • 247 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added September 9, 2026
ai-agentsgit

Security analysis

A100/100

Scanned September 9, 2026

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

Installs into .claude/skills of the current project.

Are you the author of Output Label Mapping?

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

Security grade badge for Output Label Mapping
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/vectorspacelab-output-label-mapping/badge)](https://www.skillsdirectory.com/skills/vectorspacelab-output-label-mapping)

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

SKILL.md
---
name: output_label_mapping
description: Convert frozen source-model logits or predictions to target classes with AutoVP label mapping strategies.
---
# Output Label Mapping
Use this skill for AutoVP FreqMap, IterMap-style refreshes, SemanticMap planning, or FullyMap linear logit mapping.

## Inputs
Source predictions/logits, target labels, mapping multiplicity, optional class embeddings, and optional linear weights.

## Outputs
Target-to-source mappings, target predictions, or mapped target logits.

## Workflow
For FreqMap, count source predictions per target and choose deterministic top source labels. For IterMap, recompute FreqMap after prompt updates. For FullyMap, compute `W L_s + b`. Keep tie-breaking reproducible.

## Validation
Run included deterministic tests.

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…