progress-curve-fitting
$
npx mdskill add yogsoth-ai/de-anthropocentric-research-engine/progress-curve-fittingFits performance curves to historical data for visualization and trend analysis
- Analyzes historical performance data to identify trends and inflection points
- Uses statistical curve-fitting models and time-series analysis
- Evaluates model fit quality with R-squared and residual metrics
- Exports structured results for visualization and downstream analysis
SKILL.md
.github/skills/progress-curve-fittingView on GitHub ↗
---
name: progress-curve-fitting
description: Construct performance-over-time visualization data
execution: subagent
prompt: ./prompt.md
input: historical_scores (method, score, date)
used-by: baseline-establishment
---
# Progress Curve Fitting
## Purpose
Fit parametric curves to historical SOTA performance data, identify inflection points representing paradigm shifts, and extrapolate future progress trajectories. Produces structured data suitable for visualization and trend analysis.
## Input Schema
| Field | Type | Description |
|-------|------|-------------|
| historical_scores | object[] | Array of {method, score, date, dataset, metric} sorted chronologically |
## Output Schema
```json
{
"dataset": "string",
"metric": "string",
"time_range": {"start": "string", "end": "string"},
"sota_frontier": [
{"date": "string", "method": "string", "score": 0.0, "is_new_sota": true}
],
"curve_fit": {
"best_model": "logarithmic|linear|sigmoid|exponential|piecewise",
"parameters": {},
"r_squared": 0.0,
"residual_std": 0.0
},
"inflection_points": [
{
"date": "string",
"method": "string",
"score_before": 0.0,
"score_after": 0.0,
"jump_magnitude": 0.0,
"paradigm_shift": "string"
}
],
"trend_metrics": {
"annual_improvement_rate": 0.0,
"improvement_accelerating": false,
"years_since_last_major_jump": 0.0,
"current_plateau_duration": null
},
"extrapolation": {
"predicted_1yr": 0.0,
"predicted_3yr": 0.0,
"confidence_band_1yr": [0.0, 0.0],
"confidence_band_3yr": [0.0, 0.0],
"caveat": "string"
}
}
```
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.