Score Extraction

Documents

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

View on GitHub ↗

QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

Open your project in Codex.
Copy and paste the prompt below.
Review files and risks before approving any action.

Prompt to paste

Inspect the Agent Skill at https://github.com/yogsoth-ai/de-anthropocentric-research-engine/blob/HEAD/skills/score-extraction/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/score-extraction, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

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

{
  "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"
}