Skip to content
#explainable ai Open access

ASD/BAS: Current Architecture and Historical Correspondence (v1.1)

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

Abstract

Version 1.1 update — This revision adds bounded worked examples and reader-accessibility improvements to the September 27, 2026 v1.0 publication. It also adds an explicit disclosure of AI assistance in drafting, mathematical formulation/manipulation, computational checking, adversarial review, and research organization, together with clarification of the paper’s independent-research and peer-review status. The revision does not modify ASD/BAS v2.9 canon, establish new empirical validation, or alter the paper’s principal architectural and historical claims. Applied Semantic Dynamics / Branch Admissibility System (ASD/BAS) is a formal structural research architecture for examining finite systems while keeping distinct several relations that ordinary analysis often compresses into one description. Its frozen resident model represents a finite container under load through saturation, authoritative clearance, and exit freedom, with operational wear and structural scar supplying history-sensitive dynamics. Around that resident model sit separate architectures for semantic and jurisdictional compilation, dependency and representation analysis, observation and empirical evidence, and project-level integration and governance. The present architecture is not well described as the final stage of a smooth sequence in which early qualitative papers simply became later equations. The historical record instead shows selective preservation under representational change. Some early distinctions remain visible in current architecture; others were decomposed into several typed objects, relocated to another architectural layer, represented in incompatible ways, retained primarily as methodological boundaries, or left without a demonstrated contemporary counterpart. A branch-mechanics and domain-compiler/gate-kernel line further prevents a simple linear account. This paper therefore does two jobs for a cold reader. First, it explains what the current ASD/BAS project contains and which object owns which question. Second, it gives a bounded historical correspondence map from Papers 1–31 to the current architecture while preserving discontinuity, unresolved construct identity, negative results, and unmapped claims. Historical correspondence is not treated as documented derivation. Author recollection is not treated as contemporaneous proof. Mathematical derivation is not treated as empirical validation. The result is a reader-facing project ontology plus an audited historical map, not a novelty claim, a causal genealogy, or evidence that ASD/BAS is universally valid.

View source

Similar papers

#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
#computer vision Review Apr 2024

AI-powered Code Review with LLMs: Early Results

The goal is to not only refine the accuracy of the LLM-based tool but also to underscore its potential in streamlining the software development lifecycle through proactive code improvement and education.

Z. Rasheed, Malik Abdul Sami, Muhammad Waseem et al. · 62 citations · ⚡3
#computer vision Open access Mar 2024

LLM-based agents for automating the enhancement of user story quality: An early report

The use of large language models to automatically improve the user story quality in Austrian Post Group IT agile teams is explored, with a reference model for an Autonomous LLM-based Agent System developed and implemented at the company.

Zheying Zhang, M. Rayhan, Tomas Herda et al. · 48 citations · ⚡4
#computer vision Review Mar 2024

System for systematic literature review using multiple AI agents: Concept and an empirical evaluation

This paper introduces a novel multi-AI-agent system designed to fully automate SLRs, and demonstrates how it substantially reduces the time and effort traditionally required for SLRs while maintaining comprehensiveness and precision.

Abdul Malik Sami, Z. Rasheed, Kai-Kristian Kemell et al. · 44 citations · ⚡2
#computer vision Feb 2024

Can Large Language Models Serve as Data Analysts? A Multi-Agent Assisted Approach for Qualitative Data Analysis

The proposed LLM-based multi-agent system automates qualitative data analysis process, creating opportunities for researchers and practitioners, and future improvements focus on enhancing multilingual performance and integrating continuous expert feedback.

Z. Rasheed, Muhammad Waseem, Aakash Ahmad et al. · 41 citations
#artificial intelligence Conference Open access Jun 2018

The Key Concepts of Ethics of Artificial Intelligence

It is suggested that the focus on finding keywords is the first step in guiding and providing direction for future research in the AI ethics field.

Ville Vakkuri, P. Abrahamsson · 39 citations · ⚡2

Related blog posts

Microsoft Research Blog Oct 7, 2026

Agent Lightning v1.0: A 3,500-Line Lightweight Agentic RL Framework for Training Agents with Real Harnesses

Training AI agents with reinforcement learning can be challenging because their tools, context, and decision-making are managed by complex frameworks. Agent Lightning connects existing agents to RL training, making it easier to improve them without rebuilding them. The post Agent Lightning v1.0: A 3,500-Line Lightweight Agentic RL Framework for Training Agents with Real Harnesses appeared first on Microsoft Research.

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