Skip to content
Log in
Sponsored Design Multi-Agent AI Systems Using MCP and A2A: Engineer your own Pyt Design Multi-Agent AI Systems Using MCP and A2A: Engineer your own Pyt
#artificial intelligence Open access

OASI/AERA: Operational Artificial System Intelligence Research Preview

Mohammed Messaoudene
Sep 2026 · Zenodo (CERN European Organization for Nuclear Research)

Abstract

This archive is the aggregate OASI/AERA v0.2.1 research preview. Operational Artificial System Intelligence (OASI) is the canonical name of the research paradigm; organismic computing describes its architectural hypothesis, and AERA is the bounded assurance mechanism implemented here. Operational denotes system operation, not production readiness, and the name does not claim achieved general or superintelligence, consciousness, deployment, external validation, or superiority. The archive contains the unchanged bounded Rust AERA reference runtime and tests, the v0.4 preprint and sources, specifications and claim boundaries, deterministic S5/S6 fixture data, Linux/WSL-relocatable runners qualified on WSL1 x86_64, detached aggregate checkers, tests, manifests, an SBOM, a license inventory, and reproducibility documentation. The unchanged historical Rust crate remains versioned 0.1.0-research-preview; v0.2.1 identifies the aggregate research release. The package preserves 2,700 deterministic records across 90 cells. S5 is a negative result: it did not establish an OASI advantage over the cooperative idempotent B3 receiver. S6 diagnoses a retry-versus-no-retry duplicate/omission tradeoff under a non-cooperative fixture; it does not isolate an OASI-specific mechanism advantage. Repetitions are implementation-stability traces rather than independent population samples. Fault labels denote simulated control-flow traces, not physical power loss, process termination, severed transport, or storage tearing. This release is local, fixture-only research evidence. It does not establish a complete operating system, universal effect guarantees, production or security certification, performance superiority, real-world deployment, external replication, or general superiority. Development and internal adversarial review were extensively AI-assisted and project-controlled; they are not human peer review, independent replication, certification, or institutional evaluation. Licensing is path-specific and is recorded in LICENSE_INVENTORY.json.

DOI
View source

Similar papers

#artificial intelligence Open access May 2023

Evaluating the Performance of Large Language Models on GAOKAO Benchmark

GAOKAO-Bench is introduced, an intuitive benchmark that employs questions from the Chinese GAOKAO examination as test samples, including both subjective and objective questions that contribute a robust evaluation benchmark for future large language models and offers valuable insights into the advantages and limitations of such models.

Xiaotian Zhang, Chun-yan Li, Yi Zong et al. · 216 citations · ⚡17
#artificial intelligence Open access Jul 2024

Gender, Race, and Intersectional Bias in Resume Screening via Language Model Retrieval

This work investigates the possibilities of using LLMs in a resume screening setting via a document retrieval framework that simulates job candidate selection and finds that the MTEs are biased, significantly favoring White-associated names in 85% of cases and female-associated names in only 11.1% of cases.

Kyra Wilson, Aylin Caliskan · 131 citations · ⚡8
#artificial intelligence Feb 2025

PRISM: Self-Pruning Intrinsic Selection Method for Training-Free Multimodal Data Selection

Empirically, PRISM reduces the end-to-end time for data selection and model tuning to just 30% of conventional pipelines, and achieves this efficiency while simultaneously enhancing performance, surpassing models fine-tuned on the full dataset across eight multimodal and three language understanding benchmarks.

Jinhe Bi, Yifan Wang, Danqi Yan et al. · 73 citations · ⚡4
#artificial intelligence Conference Open access Apr 2020

ECCOLA - a Method for Implementing Ethically Aligned AI Systems

The method, ECCOLA, is presented, which aims at making the high-level AI ethics principles more practical, making it possible for developers to more easily implement them in practice.

Ville Vakkuri, Kai-Kristian Kemell, P. Abrahamsson · 64 citations · ⚡6
#artificial intelligence May 2023

Let the Flows Tell: Solving Graph Combinatorial Optimization Problems with GFlowNets

This paper designs Markov decision processes (MDPs) for different combinatorial problems and proposes to train conditional GFlowNets to sample from the solution space and demonstrates that GFlowNet policies can efficiently find high-quality solutions.

Dinghuai Zhang, H. Dai, Esmeralda S. Whitammer et al. · 59 citations · ⚡8
#artificial intelligence Jun 2019

Ethically Aligned Design of Autonomous Systems: Industry viewpoint and an empirical study

An empirical study on the current state of practice in artificial intelligence ethics is conducted by means of a multiple case study of five case companies, which indicates a gap between research and practice in the area.

Ville Vakkuri, Kai-Kristian Kemell, Joni Kultanen et al. · 56 citations · ⚡6

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.