# Score Extraction

> Score Extraction is an Agent Skill for documents published in the yogsoth-ai/de-anthropocentric-research-engine repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Extract (Task, Dataset, Metric, Score, Conditions) tuples from a paper

- Skill name: `score-extraction`
- Category: [Documents](https://www.openparable.com/skill/documents/1)
- Source: https://github.com/yogsoth-ai/de-anthropocentric-research-engine/blob/HEAD/skills/score-extraction/SKILL.md
- Repository: yogsoth-ai/de-anthropocentric-research-engine (386 GitHub stars when collected)

## SKILL.md

# Score Extraction


## Purpose

Parse a paper's results sections, tables, and figures to extract all reported performance scores as structured tuples. Each tuple captures the full context needed for fair comparison: what was measured, on what data, under what conditions.

## Input Schema

| Field | Type | Description |
|-------|------|-------------|
| paper_content | string | Full paper text (markdown format) |
| target_tasks | string[] | Tasks to focus extraction on (empty = extract all) |

## Output Schema

```json
{
  "paper_title": "string",
  "scores": [
    {
      "method": "string",
      "task": "string",
      "dataset": "string",
      "split": "test|val|dev|train",
      "metric": "string",
      "score": 0.0,
      "score_std": null,
      "num_runs": null,
      "is_primary_result": true,
      "is_ablation": false,
      "table_reference": "string",
      "notes": "string"
    }
  ],
  "baselines_reported": ["string"],
  "extraction_confidence": "high|medium|low"
}
```

---

Source: https://www.openparable.com/skill/documents/score-extraction (OpenParable). Cite the canonical URL above.