Artifacts as Units of Computational Work

This technical note establishes computational artifacts as first-class objects in agent-based systems. Traditional file-based storage inadequately represents outputs that participate in multi-stage workflows — treating them as data rather than as the durable results of completed computational work. The note defines an artifact as a durable output of a completed computational process that may be referenced, verified, and reused independently of the process that produced it. Four essential characteristics are established: stable identity, derivation relationships, reusability potential, and persistence beyond the originating process. The note further establishes that artifacts naturally form dependency structures — artifact graphs — where nodes represent computational results and edges represent derivation relationships. This structural representation is foundational for understanding agent ecosystems, enabling artifact reuse, and improving computational efficiency. This is Technical Note 02 of the Agent Artifact Availability (AAA) Framework series.

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-03-11
DOI
https://doi.org/10.5281/zenodo.19059277
Primary Topic
Multi-Agent Systems and Negotiation
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Artifacts as Units of Computational Work

Rich Kopcho
Zenodo (CERN European Organization for Nuclear Research)
Multi-Agent Systems and Negotiation
article

Artifacts as Units of Computational Work

Rich Kopcho
article en

Abstract

This technical note establishes computational artifacts as first-class objects in agent-based systems. Traditional file-based storage inadequately represents outputs that participate in multi-stage workflows — treating them as data rather than as the durable results of completed computational work. The note defines an artifact as a durable output of a completed computational process that may be referenced, verified, and reused independently of the process that produced it. Four essential characteristics are established: stable identity, derivation relationships, reusability potential, and persistence beyond the originating process. The note further establishes that artifacts naturally form dependency structures — artifact graphs — where nodes represent computational results and edges represent derivation relationships. This structural representation is foundational for understanding agent ecosystems, enabling artifact reuse, and improving computational efficiency. This is Technical Note 02 of the Agent Artifact Availability (AAA) Framework series.

Zenodo (CERN European Organization for Nuclear Research)
Openalex Percentile: Top 22%
Multi-Agent Systems and Negotiation
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.