American Journal of Advanced Multidisciplinary Innovation and Research

E-ISSN: XXXX-XXXX   •   Impact Factor: -

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Call for Paper Volume 7, Issue 5 (September-October 2026) Submit your research before last 3 days of October to publish your research paper in the issue of September-October.
Submit Research Paper Join as a Reviewer

Plagiarism is checked by the leading plagiarism checker TurnItIn

Call for Paper

Volume 7 Issue 5
September-October 2026

Submit your research paper

Indexing Partners
Academia Advanced Sciences Index Bielefeld Academic Search Engine CiteSeer DRJI Google Scholar Independent Search Engine & Directory Network ISI (International Scientific Indexing) Issuu Mendeley Research Networks
RefSeek ResearcherId - Thomson Reuters ResearchGate Scirus Scribd Semantic Scholar UTeM - Universiti Teknikal Malaysia Melaka Wiki for Call for Papers WorldCat Zenodo

Machine-Learning Audit Trails for Reproducible Multidisciplinary Research

Author(s) Dr. Daniel K. Morgan
Country United States
Abstract Machine learning has become integral to multidisciplinary research in health sciences, social science, engineering, environmental studies, computational biology, economics, and other data-intensive fields. Its methodological flexibility creates substantial opportunities for discovery, but it also introduces reproducibility challenges because reported results can depend on dataset versions, preprocessing pipelines, software dependencies, random seeds, hyperparameters, hardware configurations, intermediate transformations, model checkpoints, evaluation scripts, and numerous undocumented analytical decisions. The reproducibility initiative reported by Pineau and colleagues demonstrated the importance of code submission, reproducibility checklists, and structured reporting for strengthening machine-learning research, while FAIR principles extend reproducibility concerns to data, algorithms, tools, and workflows.
This paper proposes a machine-learning audit-trail framework for reproducible multidisciplinary research. An audit trail is conceptualized as a chronological, machine-readable provenance record linking source datasets, preprocessing operations, code versions, software environments, model configurations, training runs, evaluation outputs, human decisions, derived artifacts, and publication claims. The framework integrates principles from W3C PROV, FAIR research practices, dataset documentation, model reporting, experiment tracking, and contemporary provenance systems. A conceptual-methodological research design is accompanied by a transparent simulation involving thirty minimal-audit and thirty comprehensive-audit multidisciplinary workflows. The simulated mean reproducibility score increases from 70.43 under minimal audit trails to 87.53 under comprehensive audit trails, while the median rises from 72.5 to 89.5. These values are illustrative rather than empirical measurements. The analysis suggests that reproducibility is strengthened when provenance capture extends beyond source-code availability to include datasets, execution environments, experiment lineage, parameter choices, unsuccessful runs, evaluation procedures, and links between computational artifacts and manuscript claims. The study concludes that audit trails should become persistent research infrastructure rather than retrospective documentation assembled only at publication.
Keywords machine learning, audit trails, reproducibility, research provenance, multidisciplinary research, experiment tracking, data lineage, model versioning, FAIR principles, research integrity
Field Engineering
Published In Volume 3, Issue 2, March-April 2022
Published On 2022-04-02
View / Download PDF File

Share this



E-ISSN XXXX-XXXX
CrossRef

CrossRef DOI prefix of AJAMIR is 10.00000/AJAMIR

Downloads
Research Paper Format Copyright Permission Form and Undertaking Form

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA Open Access

About AJAMIR
Fees & Payment
Current Issue
Publication Archive 		Submit Research Paper
Track Submission Status
Publication Guidelines
Publication Ethics
Peer Review & Plagiarism 		Join as a Reviewer
Editors & Reviewers
Reviewer Referral Program
Get Reviewer Membership Certi. 		Website/Journal Policies
Usage Policy
Content Policies
Privacy Policy
Contact Us +1-872-302-3851 editor@ajamir.com