Testing Explainability Compliance: Specification-Based Testing for AI Transparency

Posted on by
Academic Research
Academic Research by Oleh Ivchenko  ·  DOI: 10.5281/zenodo.20024998  63stabilfr·wdophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources0%○≥80% from editorially reviewed sources
[t]Trusted90%✓≥80% from verified, high-quality sources
[a]DOI81%✓≥80% have a Digital Object Identifier
[b]CrossRef0%○≥80% indexed in CrossRef
[i]Indexed19%○≥80% have metadata indexed
[l]Academic90%✓≥80% from journals/conferences/preprints
[f]Free Access100%✓≥80% are freely accessible
[r]References21 refs✓Minimum 10 references required
[w]Words [REQ]950✗Minimum 2,000 words for a full research article. Current: 950
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.20024998
[o]ORCID [REQ]✓✓Author ORCID verified for academic identity
[p]Peer Reviewed [REQ]—✗Peer reviewed by an assigned reviewer
[h]Freshness [REQ]71%✓≥60% of references from 2025–2026. Current: 71%
[c]Data Charts0○Original data charts from reproducible analysis (min 2). Current: 0
[g]Code—○Source code available on GitHub
[m]Diagrams1✓Mermaid architecture/flow diagrams. Current: 1
[x]Cited by0○Referenced by 0 other hub article(s)
Score = Ref Trust (70 × 60%) + Required (3/5 × 30%) + Optional (1/4 × 10%)

Explainability compliance in artificial intelligence systems demands rigorous evaluation methodologies that can verify whether AI models adhere to predefined specification criteria. This article introduces specification‑based testing (SBT) as a systematic approach to assess AI transparency, focusing on how well model outputs conform to declared functional and ethical constraints. We outline a r...

Show moreHide
Academic Research by Oleh Ivchenko DOI: 10.5281/zenodo.20024998 63stabilfr·wdophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources0%○≥80% from editorially reviewed sources
[t]Trusted90%✓≥80% from verified, high-quality sources
[a]DOI81%✓≥80% have a Digital Object Identifier
[b]CrossRef0%○≥80% indexed in CrossRef
[i]Indexed19%○≥80% have metadata indexed
[l]Academic90%✓≥80% from journals/conferences/preprints
[f]Free Access100%✓≥80% are freely accessible
[r]References21 refs✓Minimum 10 references required
[w]Words [REQ]950✗Minimum 2,000 words for a full research article. Current: 950
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.20024998
[o]ORCID [REQ]✓✓Author ORCID verified for academic identity
[p]Peer Reviewed [REQ]—✗Peer reviewed by an assigned reviewer
[h]Freshness [REQ]71%✓≥60% of references from 2025–2026. Current: 71%
[c]Data Charts0○Original data charts from reproducible analysis (min 2). Current: 0
[g]Code—○Source code available on GitHub
[m]Diagrams1✓Mermaid architecture/flow diagrams. Current: 1
[x]Cited by0○Referenced by 0 other hub article(s)
Score = Ref Trust (70 × 60%) + Required (3/5 × 30%) + Optional (1/4 × 10%)
Spec-Driven AI Dev…Read More
Read more

Formal Methods for XAI Verification: Proving That Explanations Are Correct

Posted on by
Academic Research
Academic Research by Oleh Ivchenko  ·  DOI: 10.5281/zenodo.20012331  67stabilfr·wdophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources57%○≥80% from editorially reviewed sources
[t]Trusted79%○≥80% from verified, high-quality sources
[a]DOI71%○≥80% have a Digital Object Identifier
[b]CrossRef64%○≥80% indexed in CrossRef
[i]Indexed64%○≥80% have metadata indexed
[l]Academic79%○≥80% from journals/conferences/preprints
[f]Free Access100%✓≥80% are freely accessible
[r]References14 refs✓Minimum 10 references required
[w]Words [REQ]1,014✗Minimum 2,000 words for a full research article. Current: 1,014
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.20012331
[o]ORCID [REQ]✓✓Author ORCID verified for academic identity
[p]Peer Reviewed [REQ]—✗Peer reviewed by an assigned reviewer
[h]Freshness [REQ]77%✓≥60% of references from 2025–2026. Current: 77%
[c]Data Charts0○Original data charts from reproducible analysis (min 2). Current: 0
[g]Code—○Source code available on GitHub
[m]Diagrams2✓Mermaid architecture/flow diagrams. Current: 2
[x]Cited by0○Referenced by 0 other hub article(s)
Score = Ref Trust (77 × 60%) + Required (3/5 × 30%) + Optional (1/4 × 10%)

Explainable artificial intelligence (XAI) seeks to make model decisions transparent, yet existing approaches often produce explanations that are themselves opaque or unverified. Formal verification offers a rigorous mathematical framework to certify that an explanation accurately reflects the underlying model computation. This article investigates how formal methods can be applied to XAI to gen...

Show moreHide
Academic Research by Oleh Ivchenko DOI: 10.5281/zenodo.20012331 67stabilfr·wdophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources57%○≥80% from editorially reviewed sources
[t]Trusted79%○≥80% from verified, high-quality sources
[a]DOI71%○≥80% have a Digital Object Identifier
[b]CrossRef64%○≥80% indexed in CrossRef
[i]Indexed64%○≥80% have metadata indexed
[l]Academic79%○≥80% from journals/conferences/preprints
[f]Free Access100%✓≥80% are freely accessible
[r]References14 refs✓Minimum 10 references required
[w]Words [REQ]1,014✗Minimum 2,000 words for a full research article. Current: 1,014
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.20012331
[o]ORCID [REQ]✓✓Author ORCID verified for academic identity
[p]Peer Reviewed [REQ]—✗Peer reviewed by an assigned reviewer
[h]Freshness [REQ]77%✓≥60% of references from 2025–2026. Current: 77%
[c]Data Charts0○Original data charts from reproducible analysis (min 2). Current: 0
[g]Code—○Source code available on GitHub
[m]Diagrams2✓Mermaid architecture/flow diagrams. Current: 2
[x]Cited by0○Referenced by 0 other hub article(s)
Score = Ref Trust (77 × 60%) + Required (3/5 × 30%) + Optional (1/4 × 10%)
Spec-Driven AI Dev…Read More
Read more

The EU AI Act Explanability Requirements: Technical Specification Analysis

Posted on by
AI Economics
AI Economics by Oleh Ivchenko  ·  DOI: 10.5281/zenodo.19993955  78stabilfr·wdophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources65%○≥80% from editorially reviewed sources
[t]Trusted88%✓≥80% from verified, high-quality sources
[a]DOI76%○≥80% have a Digital Object Identifier
[b]CrossRef65%○≥80% indexed in CrossRef
[i]Indexed65%○≥80% have metadata indexed
[l]Academic82%✓≥80% from journals/conferences/preprints
[f]Free Access100%✓≥80% are freely accessible
[r]References17 refs✓Minimum 10 references required
[w]Words [REQ]2,072✓Minimum 2,000 words for a full research article. Current: 2,072
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.19993955
[o]ORCID [REQ]✓✓Author ORCID verified for academic identity
[p]Peer Reviewed [REQ]—✗Peer reviewed by an assigned reviewer
[h]Freshness [REQ]80%✓≥60% of references from 2025–2026. Current: 80%
[c]Data Charts0○Original data charts from reproducible analysis (min 2). Current: 0
[g]Code✓✓Source code available on GitHub
[m]Diagrams3✓Mermaid architecture/flow diagrams. Current: 3
[x]Cited by0○Referenced by 0 other hub article(s)
Score = Ref Trust (82 × 60%) + Required (4/5 × 30%) + Optional (2/4 × 10%)

The rapid deployment of artificial intelligence systems across high‑risk domains has prompted regulators to demand greater transparency and accountability. The European Union’s Artificial Intelligence Act (EU AI Act) introduces a comprehensive framework for trustworthy AI, with particular emphasis on explicability obligations for high‑risk AI systems. This article dissects the technical specifi...

Show moreHide
AI Economics by Oleh Ivchenko DOI: 10.5281/zenodo.19993955 78stabilfr·wdophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources65%○≥80% from editorially reviewed sources
[t]Trusted88%✓≥80% from verified, high-quality sources
[a]DOI76%○≥80% have a Digital Object Identifier
[b]CrossRef65%○≥80% indexed in CrossRef
[i]Indexed65%○≥80% have metadata indexed
[l]Academic82%✓≥80% from journals/conferences/preprints
[f]Free Access100%✓≥80% are freely accessible
[r]References17 refs✓Minimum 10 references required
[w]Words [REQ]2,072✓Minimum 2,000 words for a full research article. Current: 2,072
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.19993955
[o]ORCID [REQ]✓✓Author ORCID verified for academic identity
[p]Peer Reviewed [REQ]—✗Peer reviewed by an assigned reviewer
[h]Freshness [REQ]80%✓≥60% of references from 2025–2026. Current: 80%
[c]Data Charts0○Original data charts from reproducible analysis (min 2). Current: 0
[g]Code✓✓Source code available on GitHub
[m]Diagrams3✓Mermaid architecture/flow diagrams. Current: 3
[x]Cited by0○Referenced by 0 other hub article(s)
Score = Ref Trust (82 × 60%) + Required (4/5 × 30%) + Optional (2/4 × 10%)
AI EconomicsRead More
Read more

Domain-Specific XAI Standards: Healthcare, Finance, Legal, and Defense Specifications

Posted on by
Academic Research
Academic Research by Oleh Ivchenko  ·  DOI: 10.5281/zenodo.20017366  57stabilfr·wdophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources0%○≥80% from editorially reviewed sources
[t]Trusted80%✓≥80% from verified, high-quality sources
[a]DOI60%○≥80% have a Digital Object Identifier
[b]CrossRef0%○≥80% indexed in CrossRef
[i]Indexed7%○≥80% have metadata indexed
[l]Academic73%○≥80% from journals/conferences/preprints
[f]Free Access93%✓≥80% are freely accessible
[r]References15 refs✓Minimum 10 references required
[w]Words [REQ]1,517✗Minimum 2,000 words for a full research article. Current: 1,517
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.20017366
[o]ORCID [REQ]✓✓Author ORCID verified for academic identity
[p]Peer Reviewed [REQ]—✗Peer reviewed by an assigned reviewer
[h]Freshness [REQ]64%✓≥60% of references from 2025–2026. Current: 64%
[c]Data Charts0○Original data charts from reproducible analysis (min 2). Current: 0
[g]Code✓✓Source code available on GitHub
[m]Diagrams1✓Mermaid architecture/flow diagrams. Current: 1
[x]Cited by0○Referenced by 0 other hub article(s)
Score = Ref Trust (56 × 60%) + Required (3/5 × 30%) + Optional (2/4 × 10%)

Abstract: XAI (Explainable Artificial Intelligence) has matured into a cross-disciplinary field where domain-specific standards are essential for regulatory compliance, stakeholder trust, and operational safety. While generic XAI techniques provide post-hoc explanations, industry sectors have distinct governance requirements, data sensitivity constraints, and risk tolerance levels that demand t...

Show moreHide
Academic Research by Oleh Ivchenko DOI: 10.5281/zenodo.20017366 57stabilfr·wdophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources0%○≥80% from editorially reviewed sources
[t]Trusted80%✓≥80% from verified, high-quality sources
[a]DOI60%○≥80% have a Digital Object Identifier
[b]CrossRef0%○≥80% indexed in CrossRef
[i]Indexed7%○≥80% have metadata indexed
[l]Academic73%○≥80% from journals/conferences/preprints
[f]Free Access93%✓≥80% are freely accessible
[r]References15 refs✓Minimum 10 references required
[w]Words [REQ]1,517✗Minimum 2,000 words for a full research article. Current: 1,517
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.20017366
[o]ORCID [REQ]✓✓Author ORCID verified for academic identity
[p]Peer Reviewed [REQ]—✗Peer reviewed by an assigned reviewer
[h]Freshness [REQ]64%✓≥60% of references from 2025–2026. Current: 64%
[c]Data Charts0○Original data charts from reproducible analysis (min 2). Current: 0
[g]Code✓✓Source code available on GitHub
[m]Diagrams1✓Mermaid architecture/flow diagrams. Current: 1
[x]Cited by0○Referenced by 0 other hub article(s)
Score = Ref Trust (56 × 60%) + Required (3/5 × 30%) + Optional (2/4 × 10%)
Spec-Driven AI Dev…Read More
Read more

XAI Specification Frameworks: From Natural Language to Formal Explainability Requirements

Posted on by
Academic Research
Academic Research by Oleh Ivchenko  ·  DOI: 10.5281/zenodo.19986383  58stabilfr·wdophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources0%○≥80% from editorially reviewed sources
[t]Trusted93%✓≥80% from verified, high-quality sources
[a]DOI85%✓≥80% have a Digital Object Identifier
[b]CrossRef0%○≥80% indexed in CrossRef
[i]Indexed0%○≥80% have metadata indexed
[l]Academic89%✓≥80% from journals/conferences/preprints
[f]Free Access100%✓≥80% are freely accessible
[r]References27 refs✓Minimum 10 references required
[w]Words [REQ]1,694✗Minimum 2,000 words for a full research article. Current: 1,694
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.19986383
[o]ORCID [REQ]✓✓Author ORCID verified for academic identity
[p]Peer Reviewed [REQ]—✗Peer reviewed by an assigned reviewer
[h]Freshness [REQ]58%✗≥60% of references from 2025–2026. Current: 58%
[c]Data Charts0○Original data charts from reproducible analysis (min 2). Current: 0
[g]Code✓✓Source code available on GitHub
[m]Diagrams2✓Mermaid architecture/flow diagrams. Current: 2
[x]Cited by0○Referenced by 0 other hub article(s)
Score = Ref Trust (68 × 60%) + Required (2/5 × 30%) + Optional (2/4 × 10%)

Explainable Artificial Intelligence (XAI) has emerged as a critical requirement for trustworthy AI systems, yet current approaches often treat explanations as afterthoughts rather than first-class outputs of the development process. This article proposes a specification framework for XAI that treats explainability requirements as formal specifications alongside functional requirements. We addre...

Show moreHide
Academic Research by Oleh Ivchenko DOI: 10.5281/zenodo.19986383 58stabilfr·wdophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources0%○≥80% from editorially reviewed sources
[t]Trusted93%✓≥80% from verified, high-quality sources
[a]DOI85%✓≥80% have a Digital Object Identifier
[b]CrossRef0%○≥80% indexed in CrossRef
[i]Indexed0%○≥80% have metadata indexed
[l]Academic89%✓≥80% from journals/conferences/preprints
[f]Free Access100%✓≥80% are freely accessible
[r]References27 refs✓Minimum 10 references required
[w]Words [REQ]1,694✗Minimum 2,000 words for a full research article. Current: 1,694
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.19986383
[o]ORCID [REQ]✓✓Author ORCID verified for academic identity
[p]Peer Reviewed [REQ]—✗Peer reviewed by an assigned reviewer
[h]Freshness [REQ]58%✗≥60% of references from 2025–2026. Current: 58%
[c]Data Charts0○Original data charts from reproducible analysis (min 2). Current: 0
[g]Code✓✓Source code available on GitHub
[m]Diagrams2✓Mermaid architecture/flow diagrams. Current: 2
[x]Cited by0○Referenced by 0 other hub article(s)
Score = Ref Trust (68 × 60%) + Required (2/5 × 30%) + Optional (2/4 × 10%)
Spec-Driven AI Dev…Read More
Read more

XAI for AI Auditors: Building a Cost-Effective AI Audit Practice

Posted on by
Applied Research
Applied Research by Oleh Ivchenko  ·  DOI: 10.5281/zenodo.19958723  64stabilfr·wdophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources56%○≥80% from editorially reviewed sources
[t]Trusted72%○≥80% from verified, high-quality sources
[a]DOI61%○≥80% have a Digital Object Identifier
[b]CrossRef56%○≥80% indexed in CrossRef
[i]Indexed56%○≥80% have metadata indexed
[l]Academic67%○≥80% from journals/conferences/preprints
[f]Free Access83%✓≥80% are freely accessible
[r]References18 refs✓Minimum 10 references required
[w]Words [REQ]1,215✗Minimum 2,000 words for a full research article. Current: 1,215
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.19958723
[o]ORCID [REQ]✓✓Author ORCID verified for academic identity
[p]Peer Reviewed [REQ]—✗Peer reviewed by an assigned reviewer
[h]Freshness [REQ]65%✓≥60% of references from 2025–2026. Current: 65%
[c]Data Charts0○Original data charts from reproducible analysis (min 2). Current: 0
[g]Code✓✓Source code available on GitHub
[m]Diagrams2✓Mermaid architecture/flow diagrams. Current: 2
[x]Cited by0○Referenced by 0 other hub article(s)
Score = Ref Trust (69 × 60%) + Required (3/5 × 30%) + Optional (2/4 × 10%)

The rapid adoption of artificial intelligence (AI) systems across industries has created an urgent need for auditing practices that can effectively evaluate these complex models. Traditional auditing approaches often fall short when assessing AI due to their opacity and dynamic behavior. Explainable Artificial Intelligence (XAI) offers a pathway to bridge this gap by providing interpretable ins...

Show moreHide
Applied Research by Oleh Ivchenko DOI: 10.5281/zenodo.19958723 64stabilfr·wdophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources56%○≥80% from editorially reviewed sources
[t]Trusted72%○≥80% from verified, high-quality sources
[a]DOI61%○≥80% have a Digital Object Identifier
[b]CrossRef56%○≥80% indexed in CrossRef
[i]Indexed56%○≥80% have metadata indexed
[l]Academic67%○≥80% from journals/conferences/preprints
[f]Free Access83%✓≥80% are freely accessible
[r]References18 refs✓Minimum 10 references required
[w]Words [REQ]1,215✗Minimum 2,000 words for a full research article. Current: 1,215
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.19958723
[o]ORCID [REQ]✓✓Author ORCID verified for academic identity
[p]Peer Reviewed [REQ]—✗Peer reviewed by an assigned reviewer
[h]Freshness [REQ]65%✓≥60% of references from 2025–2026. Current: 65%
[c]Data Charts0○Original data charts from reproducible analysis (min 2). Current: 0
[g]Code✓✓Source code available on GitHub
[m]Diagrams2✓Mermaid architecture/flow diagrams. Current: 2
[x]Cited by0○Referenced by 0 other hub article(s)
Score = Ref Trust (69 × 60%) + Required (3/5 × 30%) + Optional (2/4 × 10%)
Cost-Effective Ent…Read More
Read more

Human-AI Decision Support: Cost Structure of Explanation-Centric Workflows

Posted on by
Applied Research
Applied Research by Oleh Ivchenko  ·  DOI: 10.5281/zenodo.19932918  78stabilfr·wdophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources69%○≥80% from editorially reviewed sources
[t]Trusted88%✓≥80% from verified, high-quality sources
[a]DOI81%✓≥80% have a Digital Object Identifier
[b]CrossRef75%○≥80% indexed in CrossRef
[i]Indexed69%○≥80% have metadata indexed
[l]Academic88%✓≥80% from journals/conferences/preprints
[f]Free Access94%✓≥80% are freely accessible
[r]References16 refs✓Minimum 10 references required
[w]Words [REQ]2,059✓Minimum 2,000 words for a full research article. Current: 2,059
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.19932918
[o]ORCID [REQ]✓✓Author ORCID verified for academic identity
[p]Peer Reviewed [REQ]—✗Peer reviewed by an assigned reviewer
[h]Freshness [REQ]81%✓≥60% of references from 2025–2026. Current: 81%
[c]Data Charts0○Original data charts from reproducible analysis (min 2). Current: 0
[g]Code—○Source code available on GitHub
[m]Diagrams2✓Mermaid architecture/flow diagrams. Current: 2
[x]Cited by0○Referenced by 0 other hub article(s)
Score = Ref Trust (86 × 60%) + Required (4/5 × 30%) + Optional (1/4 × 10%)

Explanation-centric human-AI workflows impose hidden operational costs that are often overlooked in productivity assessments. This article examines the cost structure of maintaining explanation quality in decision-support systems, focusing on trade-offs between explanation fidelity, latency, and human cognitive load. We analyze recent empirical studies from 2025-2026 to quantify three primary c...

Show moreHide
Applied Research by Oleh Ivchenko DOI: 10.5281/zenodo.19932918 78stabilfr·wdophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources69%○≥80% from editorially reviewed sources
[t]Trusted88%✓≥80% from verified, high-quality sources
[a]DOI81%✓≥80% have a Digital Object Identifier
[b]CrossRef75%○≥80% indexed in CrossRef
[i]Indexed69%○≥80% have metadata indexed
[l]Academic88%✓≥80% from journals/conferences/preprints
[f]Free Access94%✓≥80% are freely accessible
[r]References16 refs✓Minimum 10 references required
[w]Words [REQ]2,059✓Minimum 2,000 words for a full research article. Current: 2,059
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.19932918
[o]ORCID [REQ]✓✓Author ORCID verified for academic identity
[p]Peer Reviewed [REQ]—✗Peer reviewed by an assigned reviewer
[h]Freshness [REQ]81%✓≥60% of references from 2025–2026. Current: 81%
[c]Data Charts0○Original data charts from reproducible analysis (min 2). Current: 0
[g]Code—○Source code available on GitHub
[m]Diagrams2✓Mermaid architecture/flow diagrams. Current: 2
[x]Cited by0○Referenced by 0 other hub article(s)
Score = Ref Trust (86 × 60%) + Required (4/5 × 30%) + Optional (1/4 × 10%)
Cost-Effective Ent…Read More
Read more

Interpretable Models vs Post-Hoc Explanations: True Cost Comparison for Enterprise AI

Posted on by
Applied Research
Applied Research by Oleh Ivchenko  ·  DOI: 10.5281/zenodo.19901306  54stabilfr·wdophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources18%○≥80% from editorially reviewed sources
[t]Trusted82%✓≥80% from verified, high-quality sources
[a]DOI64%○≥80% have a Digital Object Identifier
[b]CrossRef18%○≥80% indexed in CrossRef
[i]Indexed18%○≥80% have metadata indexed
[l]Academic73%○≥80% from journals/conferences/preprints
[f]Free Access100%✓≥80% are freely accessible
[r]References11 refs✓Minimum 10 references required
[w]Words [REQ]1,209✗Minimum 2,000 words for a full research article. Current: 1,209
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.19901306
[o]ORCID [REQ]✓✓Author ORCID verified for academic identity
[p]Peer Reviewed [REQ]—✗Peer reviewed by an assigned reviewer
[h]Freshness [REQ]50%✗≥60% of references from 2025–2026. Current: 50%
[c]Data Charts0○Original data charts from reproducible analysis (min 2). Current: 0
[g]Code✓✓Source code available on GitHub
[m]Diagrams2✓Mermaid architecture/flow diagrams. Current: 2
[x]Cited by0○Referenced by 0 other hub article(s)
Score = Ref Trust (62 × 60%) + Required (2/5 × 30%) + Optional (2/4 × 10%)

As enterprise AI systems proliferate across regulated industries, the choice between inherently interpretable models and post-hoc explanation techniques for complex black-box models carries significant operational, compliance, and financial implications. This article presents a comparative analysis of the total cost of ownership (TCO) for interpretable models versus post-hoc explanation approac...

Show moreHide
Applied Research by Oleh Ivchenko DOI: 10.5281/zenodo.19901306 54stabilfr·wdophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources18%○≥80% from editorially reviewed sources
[t]Trusted82%✓≥80% from verified, high-quality sources
[a]DOI64%○≥80% have a Digital Object Identifier
[b]CrossRef18%○≥80% indexed in CrossRef
[i]Indexed18%○≥80% have metadata indexed
[l]Academic73%○≥80% from journals/conferences/preprints
[f]Free Access100%✓≥80% are freely accessible
[r]References11 refs✓Minimum 10 references required
[w]Words [REQ]1,209✗Minimum 2,000 words for a full research article. Current: 1,209
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.19901306
[o]ORCID [REQ]✓✓Author ORCID verified for academic identity
[p]Peer Reviewed [REQ]—✗Peer reviewed by an assigned reviewer
[h]Freshness [REQ]50%✗≥60% of references from 2025–2026. Current: 50%
[c]Data Charts0○Original data charts from reproducible analysis (min 2). Current: 0
[g]Code✓✓Source code available on GitHub
[m]Diagrams2✓Mermaid architecture/flow diagrams. Current: 2
[x]Cited by0○Referenced by 0 other hub article(s)
Score = Ref Trust (62 × 60%) + Required (2/5 × 30%) + Optional (2/4 × 10%)
Cost-Effective Ent…Read More
Read more

XAI Tool Economics: The Cost Structure of Explanation Generation

Posted on by
AI Economics
AI Economics by Oleh Ivchenko  ·  DOI: 10.5281/zenodo.19872600  61stabilfr·wdophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources0%○≥80% from editorially reviewed sources
[t]Trusted90%✓≥80% from verified, high-quality sources
[a]DOI86%✓≥80% have a Digital Object Identifier
[b]CrossRef0%○≥80% indexed in CrossRef
[i]Indexed0%○≥80% have metadata indexed
[l]Academic90%✓≥80% from journals/conferences/preprints
[f]Free Access100%✓≥80% are freely accessible
[r]References21 refs✓Minimum 10 references required
[w]Words [REQ]1,344✗Minimum 2,000 words for a full research article. Current: 1,344
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.19872600
[o]ORCID [REQ]✓✓Author ORCID verified for academic identity
[p]Peer Reviewed [REQ]—✗Peer reviewed by an assigned reviewer
[h]Freshness [REQ]71%✓≥60% of references from 2025–2026. Current: 71%
[c]Data Charts0○Original data charts from reproducible analysis (min 2). Current: 0
[g]Code—○Source code available on GitHub
[m]Diagrams3✓Mermaid architecture/flow diagrams. Current: 3
[x]Cited by0○Referenced by 0 other hub article(s)
Score = Ref Trust (67 × 60%) + Required (3/5 × 30%) + Optional (1/4 × 10%)

Explainable Artificial Intelligence (XAI) tools are increasingly deployed to provide transparency in machine l[REDACTED]g models, yet their economic viability remains poorly understood. This article analyzes the compute and engineering costs associated with generating explanations at scale across three prominent XAI methodologies: feature attribution, counterfactual generation, and prototype-ba...

Show moreHide
AI Economics by Oleh Ivchenko DOI: 10.5281/zenodo.19872600 61stabilfr·wdophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources0%○≥80% from editorially reviewed sources
[t]Trusted90%✓≥80% from verified, high-quality sources
[a]DOI86%✓≥80% have a Digital Object Identifier
[b]CrossRef0%○≥80% indexed in CrossRef
[i]Indexed0%○≥80% have metadata indexed
[l]Academic90%✓≥80% from journals/conferences/preprints
[f]Free Access100%✓≥80% are freely accessible
[r]References21 refs✓Minimum 10 references required
[w]Words [REQ]1,344✗Minimum 2,000 words for a full research article. Current: 1,344
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.19872600
[o]ORCID [REQ]✓✓Author ORCID verified for academic identity
[p]Peer Reviewed [REQ]—✗Peer reviewed by an assigned reviewer
[h]Freshness [REQ]71%✓≥60% of references from 2025–2026. Current: 71%
[c]Data Charts0○Original data charts from reproducible analysis (min 2). Current: 0
[g]Code—○Source code available on GitHub
[m]Diagrams3✓Mermaid architecture/flow diagrams. Current: 3
[x]Cited by0○Referenced by 0 other hub article(s)
Score = Ref Trust (67 × 60%) + Required (3/5 × 30%) + Optional (1/4 × 10%)
AI EconomicsRead More
Read more

Transparent AI Sourcing: Build vs Buy Economics When Explanations Matter

Posted on by
AI Economics
AI Economics by Oleh Ivchenko  ·  DOI: 10.5281/zenodo.19858760  31stabilfr·wdophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources0%○≥80% from editorially reviewed sources
[t]Trusted50%○≥80% from verified, high-quality sources
[a]DOI25%○≥80% have a Digital Object Identifier
[b]CrossRef0%○≥80% indexed in CrossRef
[i]Indexed0%○≥80% have metadata indexed
[l]Academic50%○≥80% from journals/conferences/preprints
[f]Free Access100%✓≥80% are freely accessible
[r]References4 refs○Minimum 10 references required
[w]Words [REQ]766✗Minimum 2,000 words for a full research article. Current: 766
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.19858760
[o]ORCID [REQ]✓✓Author ORCID verified for academic identity
[p]Peer Reviewed [REQ]—✗Peer reviewed by an assigned reviewer
[h]Freshness [REQ]25%✗≥60% of references from 2025–2026. Current: 25%
[c]Data Charts0○Original data charts from reproducible analysis (min 2). Current: 0
[g]Code—○Source code available on GitHub
[m]Diagrams0○Mermaid architecture/flow diagrams. Current: 0
[x]Cited by0○Referenced by 0 other hub article(s)
Score = Ref Trust (31 × 60%) + Required (2/5 × 30%) + Optional (0/4 × 10%)

Enterprise AI procurement faces a critical dilemma: build custom solutions for tailored explainability or buy off-the-shelf platforms with faster deployment but limited transparency. This article analyzes the economic trade-offs in AI sourcing decisions when explainability requirements are paramount, drawing on the IEEE 3119-2025 standard for AI procurement and recent empirical studies. Our ana...

Show moreHide
AI Economics by Oleh Ivchenko DOI: 10.5281/zenodo.19858760 31stabilfr·wdophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources0%○≥80% from editorially reviewed sources
[t]Trusted50%○≥80% from verified, high-quality sources
[a]DOI25%○≥80% have a Digital Object Identifier
[b]CrossRef0%○≥80% indexed in CrossRef
[i]Indexed0%○≥80% have metadata indexed
[l]Academic50%○≥80% from journals/conferences/preprints
[f]Free Access100%✓≥80% are freely accessible
[r]References4 refs○Minimum 10 references required
[w]Words [REQ]766✗Minimum 2,000 words for a full research article. Current: 766
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.19858760
[o]ORCID [REQ]✓✓Author ORCID verified for academic identity
[p]Peer Reviewed [REQ]—✗Peer reviewed by an assigned reviewer
[h]Freshness [REQ]25%✗≥60% of references from 2025–2026. Current: 25%
[c]Data Charts0○Original data charts from reproducible analysis (min 2). Current: 0
[g]Code—○Source code available on GitHub
[m]Diagrams0○Mermaid architecture/flow diagrams. Current: 0
[x]Cited by0○Referenced by 0 other hub article(s)
Score = Ref Trust (31 × 60%) + Required (2/5 × 30%) + Optional (0/4 × 10%)
AI EconomicsRead More
Read more