Compose multiple FUDGE future constraints, especially topic-word constraints, by summing weighted log probabilities.
Scanned 9/9/2026
Install to Claude Code
npx -y skills add VectorSpaceLab/AREX-Skill --skill constraint_composition --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Constraint Composition?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/vectorspacelab-constraint-composition)More formats (shields.io, HTML) on the badges page.
---
name: constraint_composition
description: Compose multiple FUDGE future constraints, especially topic-word constraints, by summing weighted log probabilities.
---
# Constraint Composition for Topics
Use this skill when a FUDGE decoder must condition on several target words or independent attributes. For topic control, compute `(lambda/N) * sum_j log P(w_j | prefix+candidate)`.
## Inputs
- Candidate-to-target probability table.
- Ordered list of target words or attributes.
- `lambda_value` and whether to normalize by `N`.
## Outputs
- Composed future log score per candidate.
- Audit contributions per candidate and per target.
## Workflow
1. Ensure every candidate has every target probability.
2. Clip probabilities to avoid log(0).
3. Compute the target weight.
4. Sum weighted log-probability contributions.
5. Pass the composed score to the FUDGE rescoring skill.
## Validation
Run `python tests/test_composition.py`.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Practical guide to testing web applications with screen readers for comprehensive accessibility validation.
在编写新功能、修复错误或重构代码时使用此技能。强制执行测试驱动开发,包含单元测试、集成测试和端到端测试,覆盖率超过80%。
Go测试模式包括表格驱动测试、子测试、基准测试、模糊测试和测试覆盖率。遵循TDD方法论,采用地道的Go实践。
Django测试策略,包括pytest-django、TDD方法论、factory_boy、模拟、覆盖率以及测试Django REST Framework API。
克劳德代码会话的正式评估框架,实施评估驱动开发(EDD)原则