EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

FairStack AI: AI-Enabled Orchestration of a Scientific Data Software Stack

Cifeng Wang, Zhaochen Wu, Junlei Duan, Lei Jiang, Changfa Lu

Applied Sciences · 16.11.2026 · 16 (22) · 11350

DOI: 10.3390/app162211350 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 16.11.2026. Verfasst von Cifeng Wang und 4 weiteren Autor:innen. Die Arbeit nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Chinese Academy of Sciences.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Scientific data centers must coordinate many specialized tools to complete submission records, build data-asset inventories, and assess data quality. Standardized software stacks provide these tools, but the workflow still requires substantial manual interpretation, cross-system coordination, and compliance review. We present FairStack AI V1.0, an orchestration framework that encodes the domain specification as versioned rule artifacts and enforces three runtime constraints—Gate, Contract, and Abstain—across a three-stage submission lifecycle. The order of operations is fixed by the specification, so the agent determines content rather than sequence; operations not permitted at a stage are refused, not attempted, and ambiguous or compliance-critical values go to a human operator. The framework is implemented on FairStack and evaluated on all 200 de-identified National Key Research and Development Program projects. Data-asset inventories attain a graded match score of 0.803 (precision 0.864, recall 0.751) against the reference plans and recover 3927 of the 5029 reference entries; omissions outnumber unsupported assertions by about four to one, so the residual error is one of coverage rather than of correctness. Contract compliance holds at runtime: 96.3% of entries carry all eleven prescribed keys under their prescribed spellings, free-text names reach 0.754 average cosine similarity with the human reference, and the top-level container shape is identical in all 200 runs. On the machine side a project completes in a median of 26.7 min over 1.09 agent rounds. The results show that rule constraints reduce repetitive work while a human operator retains every ambiguous or compliance-critical decision, and that an externalized specification makes both the shape and the completeness of the output mechanically checkable against the source.

Förderung

  • Chinese Academy of Sciences

Zitieren

APA

Wang, C., Wu, Z., Duan, J., Jiang, L., & Lu, C. (2026). FairStack AI: AI-Enabled Orchestration of a Scientific Data Software Stack. Applied Sciences, 16(22), 11350. https://doi.org/10.3390/app162211350

Vancouver

Wang C, Wu Z, Duan J, Jiang L, Lu C. FairStack AI: AI-Enabled Orchestration of a Scientific Data Software Stack. Applied Sciences. 2026;16(22):11350. doi:10.3390/app162211350

BibTeX
@article{Wang2026,
  author = {Wang, Cifeng and Wu, Zhaochen and Duan, Junlei and Jiang, Lei and Lu, Changfa},
  title = {FairStack AI: AI-Enabled Orchestration of a Scientific Data Software Stack},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {22},
  pages = {11350},
  doi = {10.3390/app162211350}
}
Kostenlos starten →