name: score-extraction
description: Extract (Task, Dataset, Metric, Score, Conditions) tuples from a paper
execution: subagent
prompt: ./prompt.md
input: paper_content, target_tasks
used-by: baseline-establishment
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"
}
1---2name: score-extraction-23description: "---"4---5---6name: score-extraction7description: Extract (Task, Dataset, Metric, Score, Conditions) tuples from a paper8execution: subagent9prompt: ./prompt.md10input: paper_content, target_tasks11used-by: baseline-establishment12---1314# Score Extraction151617## Purpose1819Parse 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.2021## Input Schema2223| Field | Type | Description |24|-------|------|-------------|25| paper_content | string | Full paper text (markdown format) |26| target_tasks | string[] | Tasks to focus extraction on (empty = extract all) |2728## Output Schema2930```json31{32 "paper_title": "string",33 "scores": [34 {35 "method": "string",36 "task": "string",37 "dataset": "string",38 "split": "test|val|dev|train",39 "metric": "string",40 "score": 0.0,41 "score_std": null,42 "num_runs": null,43 "is_primary_result": true,44 "is_ablation": false,45 "table_reference": "string",46 "notes": "string"47 }48 ],49 "baselines_reported": ["string"],50 "extraction_confidence": "high|medium|low"51}52```