structural-counterfactual
$
npx mdskill add yogsoth-ai/de-anthropocentric-research-engine/structural-counterfactualPearl Three-Step: Abduction, Action, Prediction applied to artifact validation.
SKILL.md
.github/skills/structural-counterfactualView on GitHub ↗
---
name: structural-counterfactual
description: "Strategy: Pearl Three-Step counterfactual — Abduction (fit model to evidence), Action (intervene on factor), Prediction (derive counterfactual outcome)."
type: strategy
used-by: [counterfactual-probing]
tactics: [systematic-factor-ablation, causal-necessity-testing]
---
# Structural Counterfactual Strategy
Pearl Three-Step: Abduction, Action, Prediction applied to artifact validation.
## Method
1. **causal-claim-extraction** identifies causal structure in the artifact
2. **factor-enumeration** lists all factors in the causal model
3. **Abduction**: fit background variables to observed evidence
4. **Action**: **single-factor-removal** intervenes on one factor at a time
5. **Prediction**: **counterfactual-scenario-construction** derives new outcome
6. **necessity-evaluation** and **sufficiency-evaluation** score each factor
7. **load-bearing-identification** synthesizes results
## Budget Table
| Parameter | S | M | L |
|---|---|---|---|
| Factors modeled | 5 | 10 | 20 |
| Interventions per factor | 1 | 2 | 4 |
| Prediction depth | 2 | 4 | 8 |
## Orchestration
```
causal-claim-extraction → factor-enumeration
→ [for each factor]:
single-factor-removal (abduction + action)
→ counterfactual-scenario-construction (prediction)
→ necessity-evaluation + sufficiency-evaluation
→ load-bearing-identification → fragility-measurement
```
## Subagents
- causal-claim-extraction (model building)
- factor-enumeration (variable identification)
- single-factor-removal (intervention)
- counterfactual-scenario-construction (prediction)
- necessity-evaluation (PN scoring)
- sufficiency-evaluation (PS scoring)
- load-bearing-identification (synthesis)
- fragility-measurement (aggregation)
More from yogsoth-ai/de-anthropocentric-research-engine
- abductive-hypothesis-generationStrategy: 面对异常的最佳解释推理
- ablation-brainstormRemove components one by one, observe system changes to reveal hidden dependencies and generate ideas from structural gaps.
- ablation-component-mappingMap system architecture to ablatable units for ablation studies
- ablation-designDesign ablation studies to isolate component contributions in ML systems
- ablation-executionRemove components one by one from a system, record the response/impact of each removal.
- abp-vulnerability-classificationClassify assumptions on 2 axes — load-bearing (how much conclusion depends on it) × vulnerable (how likely to be false). Focuses attention on High-Load × High-Vulnerable quadrant.
- abstraction-extractionExtract abstract principles from concrete domain cases. Strips domain-specific details to reveal transferable mechanisms.
- abstraction-ladderPerform bisociation at multiple abstraction levels
- abstraction-ladderingMove between concrete and abstract framings — 3 levels up (Why?) and 3 levels down (How?) to find the most productive research level.
- abstraction-to-designAbstract biological principle to design principle. Bridge from biology to engineering.