Abstract

This paper presents the Stabilarity Research Platform — an open, API-accessible research infrastructure exposing validated machine learning models, geopolitical risk datasets, and decision optimization tools to the global research community at no cost. The platform implements FAIR data principles (Wilkinson et al., 2016), providing composable, versioned endpoints for: (1) medical imaging classification across six diagnostic domains (Pesapane et al., 2022); (2) country-level geopolitical risk quantification using GDELT (Leetaru & Schrodt, 2013) and ACLED (Raleigh et al., 2010) event data; (3) pharmaceutical portfolio optimization via the Decision Readiness Index (DRI) framework; and (4) enterprise AI decision support tools. All systems are versioned, documented, and accessible via personal API keys issued at no cost to community members, consistent with emerging norms in research software citation (Katz et al., 2021).

graph TD
    API["Stabilarity API v1
hub.stabilarity.com/api/v1/"]
    MED["Medical AI Module
/scanlab/"]
    GEO["Geopolitical Risk Module
/geo-risk/"]
    DRI["DRI Optimizer Module
/dri/"]
    DS["Decision Support Module
/enterprise-ai/"]
    AUTH["Authentication
X-API-Key header"]
    AUTH --> API
    API --> MED
    API --> GEO
    API --> DRI
    API --> DS
    MED --> M1["Chest X-ray · CT · Dermoscopy
Ophthalmology · Pathology · Brain MRI"]
    GEO --> G1["Country Risk Scores
GDELT + ACLED datasets"]
    DRI --> D1["Decision Readiness Index
Pharma Portfolio Optimization"]
    DS --> E1["Enterprise ML Tools
Prediction · Classification"]
    style API fill:#000,color:#fff,stroke:#000
    style AUTH fill:#e8f5e9,stroke:#2e7d32

We have been building research tools, training ML models, and assembling geopolitical and economic datasets for the past two years. Today, all of it is open — programmatically, via a unified API — free for every researcher who wants to build on top of what we have built. This approach aligns with the growing consensus that scientific data and tools should be made FAIR: Findable, Accessible, Interoperable, and Reusable (Stall et al., 2019).

This is not a product launch. There is no pricing page, no trial period, no sales call. It is a research platform, built by researchers, opened to researchers. If you are a member of the Stabilarity community, your personal API key is already waiting for you.

flowchart LR
    RAW["Raw Event Data
GDELT · ACLED · News"]
    PROC["Data Processing Pipeline
Normalization · Deduplication"]
    MODEL["Risk Quantification Model
Country-level scoring"]
    CACHE["Dataset Cache
Versioned snapshots"]
    API2["REST API Endpoint
/geo-risk/data/countries"]
    VIZ["Visualization Endpoint
/geo-risk/chart/world-map"]
    RAW --> PROC
    PROC --> MODEL
    MODEL --> CACHE
    CACHE --> API2
    CACHE --> VIZ
    style RAW fill:#fff3cd,stroke:#856404
    style MODEL fill:#cce5ff,stroke:#004085
    style API2 fill:#d4edda,stroke:#155724
    style VIZ fill:#d4edda,stroke:#155724

graph TD
    INPUT["Researcher Request
Research question + API key"]
    ROUTE["API Router
Endpoint selection"]
    SCAN["ScanLab
Medical imaging inference"]
    RISK["GeoRisk
Country risk dataset"]
    OPT["DRI Optimizer
Portfolio decision framework"]
    OUT1["JSON response +
confidence scores"]
    OUT2["Risk scores +
trend data + charts"]
    OUT3["DRI scores +
optimization recommendations"]
    CITE["Research Citation
DOI: 10.5281/zenodo.18928330"]
    INPUT --> ROUTE
    ROUTE --> SCAN --> OUT1
    ROUTE --> RISK --> OUT2
    ROUTE --> OPT --> OUT3
    OUT1 --> CITE
    OUT2 --> CITE
    OUT3 --> CITE
    style INPUT fill:#e3f2fd,stroke:#1565c0
    style CITE fill:#f3e5f5,stroke:#6a1b9a

References

• Ardila, D., et al. (2019). End-to-end lung cancer detection on CT with deep learning. Nature Medicine, 25, 954–961. https://doi.org/10.1038/s41591-019-0447-x
• Katz, D.S., et al. (2021). A Fresh Look at the Software Citation Principles. PeerJ Computer Science. https://doi.org/10.7717/peerj-cs.659
• Leetaru, K. & Schrodt, P.A. (2013). GDELT: Global Data on Events, Location and Tone. ISA Annual Convention. https://www.gdeltproject.org/
• Pesapane, F., et al. (2022). Artificial intelligence as a medical device in radiology. European Radiology. https://doi.org/10.1007/s00330-021-08408-x
• Raleigh, C., et al. (2010). Introducing ACLED: An Armed Conflict Location and Event Dataset. Journal of Peace Research, 47(5), 651–660. https://doi.org/10.1177/0022343310370914
• Stall, S., et al. (2019). Make scientific data FAIR. Nature, 570, 27–29. https://doi.org/10.1038/d41586-019-01720-7
• Wilkinson, M.D., et al. (2016). The FAIR Guiding Principles for scientific data management and stewardship. Nature Scientific Data, 3, 160018. https://doi.org/10.1038/sdata.2016.18

Further Reading

📖 Beyond the Benchmark: What AI Looks Like When It Actually Works — A journal-level examination of each platform system, how they compose, and why openness matters for research adoption. DOI: DOI pending — scientific review in progress