Category: Spec-Driven AI Development

Comprehensive overview of spec-driven AI development in enterprise

Post-Deployment XAI Monitoring: Specification Requirements for Explanation Drift Detection

Posted on by
Academic Research
Academic Research by Oleh Ivchenko  ·  DOI: 10.5281/zenodo.20347195  53stabilfr·wdophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources0%○≥80% from editorially reviewed sources
[t]Trusted100%✓≥80% from verified, high-quality sources
[a]DOI50%○≥80% have a Digital Object Identifier
[b]CrossRef0%○≥80% indexed in CrossRef
[i]Indexed0%○≥80% have metadata indexed
[l]Academic100%✓≥80% from journals/conferences/preprints
[f]Free Access100%✓≥80% are freely accessible
[r]References2 refs○Minimum 10 references required
[w]Words [REQ]1,320✗Minimum 2,000 words for a full research article. Current: 1,320
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.20347195
[o]ORCID [REQ]✓✓Author ORCID verified for academic identity
[p]Peer Reviewed [REQ]—✗Peer reviewed by an assigned reviewer
[h]Freshness [REQ]100%✓≥60% of references from 2025–2026. Current: 100%
[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 (59 × 60%) + Required (3/5 × 30%) + Optional (0/4 × 10%)

Post-deployment monitoring of explainable AI (XAI) systems has emerged as a critical concern for maintaining trustworthy AI behaviors over time [1]. While pre-deployment validation establishes baseline explanation quality, it does not guarantee sustained performance when models encounter distribution shifts, concept drift, or evolving user expectations [2]. This article addresses the research g...

Show moreHide
Academic Research by Oleh Ivchenko DOI: 10.5281/zenodo.20347195 53stabilfr·wdophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources0%○≥80% from editorially reviewed sources
[t]Trusted100%✓≥80% from verified, high-quality sources
[a]DOI50%○≥80% have a Digital Object Identifier
[b]CrossRef0%○≥80% indexed in CrossRef
[i]Indexed0%○≥80% have metadata indexed
[l]Academic100%✓≥80% from journals/conferences/preprints
[f]Free Access100%✓≥80% are freely accessible
[r]References2 refs○Minimum 10 references required
[w]Words [REQ]1,320✗Minimum 2,000 words for a full research article. Current: 1,320
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.20347195
[o]ORCID [REQ]✓✓Author ORCID verified for academic identity
[p]Peer Reviewed [REQ]—✗Peer reviewed by an assigned reviewer
[h]Freshness [REQ]100%✓≥60% of references from 2025–2026. Current: 100%
[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 (59 × 60%) + Required (3/5 × 30%) + Optional (0/4 × 10%)
Spec-Driven AI Dev…Read More
Read more

Human-Readable AI Explanations: Specification for Audience-Appropriate Transparency

Posted on by
Academic Research
Academic Research by Oleh Ivchenko  ·  DOI: 10.5281/zenodo.20303709  77stabilfr·wdophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources69%○≥80% from editorially reviewed sources
[t]Trusted100%✓≥80% from verified, high-quality sources
[a]DOI92%✓≥80% have a Digital Object Identifier
[b]CrossRef69%○≥80% indexed in CrossRef
[i]Indexed69%○≥80% have metadata indexed
[l]Academic100%✓≥80% from journals/conferences/preprints
[f]Free Access100%✓≥80% are freely accessible
[r]References13 refs✓Minimum 10 references required
[w]Words [REQ]698✗Minimum 2,000 words for a full research article. Current: 698
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.20303709
[o]ORCID [REQ]✓✓Author ORCID verified for academic identity
[p]Peer Reviewed [REQ]—✗Peer reviewed by an assigned reviewer
[h]Freshness [REQ]75%✓≥60% of references from 2025–2026. Current: 75%
[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 (94 × 60%) + Required (3/5 × 30%) + Optional (1/4 × 10%)

The proliferation of artificial intelligence systems has foregrounded the need for explanations that are not only technically accurate but also tailored to the cognitive and professional contexts of diverse stakeholders. This article establishes a systematic specification framework for generating audience‑appropriate explanations of AI decisions, bridging the gap between model‑level transparenc...

Show moreHide
Academic Research by Oleh Ivchenko DOI: 10.5281/zenodo.20303709 77stabilfr·wdophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources69%○≥80% from editorially reviewed sources
[t]Trusted100%✓≥80% from verified, high-quality sources
[a]DOI92%✓≥80% have a Digital Object Identifier
[b]CrossRef69%○≥80% indexed in CrossRef
[i]Indexed69%○≥80% have metadata indexed
[l]Academic100%✓≥80% from journals/conferences/preprints
[f]Free Access100%✓≥80% are freely accessible
[r]References13 refs✓Minimum 10 references required
[w]Words [REQ]698✗Minimum 2,000 words for a full research article. Current: 698
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.20303709
[o]ORCID [REQ]✓✓Author ORCID verified for academic identity
[p]Peer Reviewed [REQ]—✗Peer reviewed by an assigned reviewer
[h]Freshness [REQ]75%✓≥60% of references from 2025–2026. Current: 75%
[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 (94 × 60%) + Required (3/5 × 30%) + Optional (1/4 × 10%)
Spec-Driven AI Dev…Read More
Read more

XAI for High-Stakes Decisions: Extra-Specification Requirements for Critical AI

Posted on by
Academic Research
Academic Research by Oleh Ivchenko  ·  DOI: 10.5281/zenodo.20256715  64stabilfr·wdophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources0%○≥80% from editorially reviewed sources
[t]Trusted100%✓≥80% from verified, high-quality sources
[a]DOI85%✓≥80% have a Digital Object Identifier
[b]CrossRef0%○≥80% indexed in CrossRef
[i]Indexed10%○≥80% have metadata indexed
[l]Academic100%✓≥80% from journals/conferences/preprints
[f]Free Access100%✓≥80% are freely accessible
[r]References48 refs✓Minimum 10 references required
[w]Words [REQ]1,721✗Minimum 2,000 words for a full research article. Current: 1,721
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.20256715
[o]ORCID [REQ]✓✓Author ORCID verified for academic identity
[p]Peer Reviewed [REQ]—✗Peer reviewed by an assigned reviewer
[h]Freshness [REQ]85%✓≥60% of references from 2025–2026. Current: 85%
[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 (73 × 60%) + Required (3/5 × 30%) + Optional (1/4 × 10%)

The deployment of AI systems in high-stakes domains such as healthcare, finance, and autonomous infrastructure demands rigorous specification of behavioral expectations. Existing regulatory frameworks often lack the granularity required to capture the multifaceted nature of these systems, leading to gaps between intended safety guarantees and actual operational realities. This article investiga...

Show moreHide
Academic Research by Oleh Ivchenko DOI: 10.5281/zenodo.20256715 64stabilfr·wdophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources0%○≥80% from editorially reviewed sources
[t]Trusted100%✓≥80% from verified, high-quality sources
[a]DOI85%✓≥80% have a Digital Object Identifier
[b]CrossRef0%○≥80% indexed in CrossRef
[i]Indexed10%○≥80% have metadata indexed
[l]Academic100%✓≥80% from journals/conferences/preprints
[f]Free Access100%✓≥80% are freely accessible
[r]References48 refs✓Minimum 10 references required
[w]Words [REQ]1,721✗Minimum 2,000 words for a full research article. Current: 1,721
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.20256715
[o]ORCID [REQ]✓✓Author ORCID verified for academic identity
[p]Peer Reviewed [REQ]—✗Peer reviewed by an assigned reviewer
[h]Freshness [REQ]85%✓≥60% of references from 2025–2026. Current: 85%
[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 (73 × 60%) + Required (3/5 × 30%) + Optional (1/4 × 10%)
Spec-Driven AI Dev…Read More
Read more

Explanation Quality Specifications: Metrics, Thresholds, and Acceptance Criteria for XAI

Posted on by
Academic Research
Academic Research by Oleh Ivchenko  ·  DOI: 10.5281/zenodo.20248503  53stabilfr·wdophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources0%○≥80% from editorially reviewed sources
[t]Trusted100%✓≥80% from verified, high-quality sources
[a]DOI67%○≥80% have a Digital Object Identifier
[b]CrossRef0%○≥80% indexed in CrossRef
[i]Indexed0%○≥80% have metadata indexed
[l]Academic100%✓≥80% from journals/conferences/preprints
[f]Free Access100%✓≥80% are freely accessible
[r]References3 refs○Minimum 10 references required
[w]Words [REQ]1,277✗Minimum 2,000 words for a full research article. Current: 1,277
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.20248503
[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]Diagrams3✓Mermaid architecture/flow diagrams. Current: 3
[x]Cited by0○Referenced by 0 other hub article(s)
Score = Ref Trust (64 × 60%) + Required (2/5 × 30%) + Optional (1/4 × 10%)

Explainable Artificial Intelligence (XAI) seeks to make model decisions transparent and understandable to diverse stakeholders. However, the notion of an “acceptable” explanation remains under-specified, lacking consensus on quantitative criteria. This article formalizes explanation quality by defining three interrelated research questions: (RQ1) what fidelity thresholds guarantee faithful repr...

Show moreHide
Academic Research by Oleh Ivchenko DOI: 10.5281/zenodo.20248503 53stabilfr·wdophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources0%○≥80% from editorially reviewed sources
[t]Trusted100%✓≥80% from verified, high-quality sources
[a]DOI67%○≥80% have a Digital Object Identifier
[b]CrossRef0%○≥80% indexed in CrossRef
[i]Indexed0%○≥80% have metadata indexed
[l]Academic100%✓≥80% from journals/conferences/preprints
[f]Free Access100%✓≥80% are freely accessible
[r]References3 refs○Minimum 10 references required
[w]Words [REQ]1,277✗Minimum 2,000 words for a full research article. Current: 1,277
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.20248503
[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]Diagrams3✓Mermaid architecture/flow diagrams. Current: 3
[x]Cited by0○Referenced by 0 other hub article(s)
Score = Ref Trust (64 × 60%) + Required (2/5 × 30%) + Optional (1/4 × 10%)
Spec-Driven AI Dev…Read More
Read more

Real-Time XAI Specifications: Performance Requirements for Production Explanations

Posted on by
Academic Research
Academic Research by Oleh Ivchenko  76stabilfr·wdophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources0%○≥80% from editorially reviewed sources
[t]Trusted100%✓≥80% from verified, high-quality sources
[a]DOI97%✓≥80% have a Digital Object Identifier
[b]CrossRef0%○≥80% indexed in CrossRef
[i]Indexed95%✓≥80% have metadata indexed
[l]Academic100%✓≥80% from journals/conferences/preprints
[f]Free Access100%✓≥80% are freely accessible
[r]References65 refs✓Minimum 10 references required
[w]Words [REQ]2,290✓Minimum 2,000 words for a full research article. Current: 2,290
[d]DOI [REQ]✗✗Zenodo DOI registered for persistent citation
[o]ORCID [REQ]✓✓Author ORCID verified for academic identity
[p]Peer Reviewed [REQ]—✗Peer reviewed by an assigned reviewer
[h]Freshness [REQ]100%✓≥60% of references from 2025–2026. Current: 100%
[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 (93 × 60%) + Required (3/5 × 30%) + Optional (1/4 × 10%)

The rapid deployment of AI-driven decision systems in production environments has intensified the demand for explanation generation that is not only semantically meaningful but also temporally bounded and resource-constrained. This article establishes a formal specification framework for real-time explainability, defining precise performance requirements for latency, fidelity, and computational...

Show moreHide
Academic Research by Oleh Ivchenko 76stabilfr·wdophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources0%○≥80% from editorially reviewed sources
[t]Trusted100%✓≥80% from verified, high-quality sources
[a]DOI97%✓≥80% have a Digital Object Identifier
[b]CrossRef0%○≥80% indexed in CrossRef
[i]Indexed95%✓≥80% have metadata indexed
[l]Academic100%✓≥80% from journals/conferences/preprints
[f]Free Access100%✓≥80% are freely accessible
[r]References65 refs✓Minimum 10 references required
[w]Words [REQ]2,290✓Minimum 2,000 words for a full research article. Current: 2,290
[d]DOI [REQ]✗✗Zenodo DOI registered for persistent citation
[o]ORCID [REQ]✓✓Author ORCID verified for academic identity
[p]Peer Reviewed [REQ]—✗Peer reviewed by an assigned reviewer
[h]Freshness [REQ]100%✓≥60% of references from 2025–2026. Current: 100%
[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 (93 × 60%) + Required (3/5 × 30%) + Optional (1/4 × 10%)
Spec-Driven AI Dev…Read More
Read more

Cross-Border AI Explanation Requirements: Specifying XAI for Multi-Jurisdictional Compliance

Posted on by
Academic Research
Academic Research by Oleh Ivchenko  51stabilfr·wdophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources0%○≥80% from editorially reviewed sources
[t]Trusted81%✓≥80% from verified, high-quality sources
[a]DOI69%○≥80% have a Digital Object Identifier
[b]CrossRef0%○≥80% indexed in CrossRef
[i]Indexed12%○≥80% have metadata indexed
[l]Academic77%○≥80% from journals/conferences/preprints
[f]Free Access92%✓≥80% are freely accessible
[r]References26 refs✓Minimum 10 references required
[w]Words [REQ]1,947✗Minimum 2,000 words for a full research article. Current: 1,947
[d]DOI [REQ]✗✗Zenodo DOI registered for persistent citation
[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]Diagrams3✓Mermaid architecture/flow diagrams. Current: 3
[x]Cited by0○Referenced by 0 other hub article(s)
Score = Ref Trust (61 × 60%) + Required (2/5 × 30%) + Optional (1/4 × 10%)

Artificial intelligence systems are increasingly deployed across jurisdictions that impose distinct obligations on the transparency and interpretability of model decisions. While the European Union’s AI Act establishes a comprehensive framework for high‑risk AI, the United States relies on sector‑specific Executive Orders and guidance from the National Institute of Standards and Technology (NIS...

Show moreHide
Academic Research by Oleh Ivchenko 51stabilfr·wdophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources0%○≥80% from editorially reviewed sources
[t]Trusted81%✓≥80% from verified, high-quality sources
[a]DOI69%○≥80% have a Digital Object Identifier
[b]CrossRef0%○≥80% indexed in CrossRef
[i]Indexed12%○≥80% have metadata indexed
[l]Academic77%○≥80% from journals/conferences/preprints
[f]Free Access92%✓≥80% are freely accessible
[r]References26 refs✓Minimum 10 references required
[w]Words [REQ]1,947✗Minimum 2,000 words for a full research article. Current: 1,947
[d]DOI [REQ]✗✗Zenodo DOI registered for persistent citation
[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]Diagrams3✓Mermaid architecture/flow diagrams. Current: 3
[x]Cited by0○Referenced by 0 other hub article(s)
Score = Ref Trust (61 × 60%) + Required (2/5 × 30%) + Optional (1/4 × 10%)
Spec-Driven AI Dev…Read More
Read more

The ISO/IEC 24027 Bias in AI Explanations: Specification Implications

Posted on by
Academic Research
Academic Research by Oleh Ivchenko  ·  DOI: 10.5281/zenodo.20095806  49stabilfr·wdophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources0%○≥80% from editorially reviewed sources
[t]Trusted83%✓≥80% from verified, high-quality sources
[a]DOI67%○≥80% have a Digital Object Identifier
[b]CrossRef0%○≥80% indexed in CrossRef
[i]Indexed0%○≥80% have metadata indexed
[l]Academic75%○≥80% from journals/conferences/preprints
[f]Free Access100%✓≥80% are freely accessible
[r]References12 refs✓Minimum 10 references required
[w]Words [REQ]1,774✗Minimum 2,000 words for a full research article. Current: 1,774
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.20095806
[o]ORCID [REQ]✓✓Author ORCID verified for academic identity
[p]Peer Reviewed [REQ]—✗Peer reviewed by an assigned reviewer
[h]Freshness [REQ]18%✗≥60% of references from 2025–2026. Current: 18%
[c]Data Charts0○Original data charts from reproducible analysis (min 2). Current: 0
[g]Code—○Source code available on GitHub
[m]Diagrams4✓Mermaid architecture/flow diagrams. Current: 4
[x]Cited by0○Referenced by 0 other hub article(s)
Score = Ref Trust (58 × 60%) + Required (2/5 × 30%) + Optional (1/4 × 10%)

Explainability frameworks increasingly intertwine technical desiderata with normative commitments, yet the standards community struggles to reconcile algorithmic transparency with equitable outcomes. ISO/IEC 24027—Artificial intelligence—Explainability requirements for AI systems—offers the first international attempt to codify explanatory integrity, but its pragmatic implementation e[REDACTED]...

Show moreHide
Academic Research by Oleh Ivchenko DOI: 10.5281/zenodo.20095806 49stabilfr·wdophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources0%○≥80% from editorially reviewed sources
[t]Trusted83%✓≥80% from verified, high-quality sources
[a]DOI67%○≥80% have a Digital Object Identifier
[b]CrossRef0%○≥80% indexed in CrossRef
[i]Indexed0%○≥80% have metadata indexed
[l]Academic75%○≥80% from journals/conferences/preprints
[f]Free Access100%✓≥80% are freely accessible
[r]References12 refs✓Minimum 10 references required
[w]Words [REQ]1,774✗Minimum 2,000 words for a full research article. Current: 1,774
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.20095806
[o]ORCID [REQ]✓✓Author ORCID verified for academic identity
[p]Peer Reviewed [REQ]—✗Peer reviewed by an assigned reviewer
[h]Freshness [REQ]18%✗≥60% of references from 2025–2026. Current: 18%
[c]Data Charts0○Original data charts from reproducible analysis (min 2). Current: 0
[g]Code—○Source code available on GitHub
[m]Diagrams4✓Mermaid architecture/flow diagrams. Current: 4
[x]Cited by0○Referenced by 0 other hub article(s)
Score = Ref Trust (58 × 60%) + Required (2/5 × 30%) + Optional (1/4 × 10%)
Spec-Driven AI Dev…Read More
Read more

Adversarial Robustness in XAI Specifications: Why Explainability Must Be Secure

Posted on by
Academic Research
Academic Research by Oleh Ivchenko  ·  DOI: 10.5281/zenodo.20059169  66stabilfr·wdophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources0%○≥80% from editorially reviewed sources
[t]Trusted81%✓≥80% from verified, high-quality sources
[a]DOI75%○≥80% have a Digital Object Identifier
[b]CrossRef0%○≥80% indexed in CrossRef
[i]Indexed19%○≥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]2,380✓Minimum 2,000 words for a full research article. Current: 2,380
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.20059169
[o]ORCID [REQ]✓✓Author ORCID verified for academic identity
[p]Peer Reviewed [REQ]—✗Peer reviewed by an assigned reviewer
[h]Freshness [REQ]69%✓≥60% of references from 2025–2026. Current: 69%
[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 (65 × 60%) + Required (4/5 × 30%) + Optional (1/4 × 10%)

Explainability (XAI) systems are increasingly deployed in safety-critical domains, yet their vulnerability to adversarial manipulation threatens trust and decision integrity. This article investigates the adversarial robustness of specification-based XAI mechanisms, focusing on how malicious inputs can subvert explanatory outputs without altering the underlying model behavior. We pose three cor...

Show moreHide
Academic Research by Oleh Ivchenko DOI: 10.5281/zenodo.20059169 66stabilfr·wdophcgmx
BadgeMetricValueStatusDescription
[s]Reviewed Sources0%○≥80% from editorially reviewed sources
[t]Trusted81%✓≥80% from verified, high-quality sources
[a]DOI75%○≥80% have a Digital Object Identifier
[b]CrossRef0%○≥80% indexed in CrossRef
[i]Indexed19%○≥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]2,380✓Minimum 2,000 words for a full research article. Current: 2,380
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.20059169
[o]ORCID [REQ]✓✓Author ORCID verified for academic identity
[p]Peer Reviewed [REQ]—✗Peer reviewed by an assigned reviewer
[h]Freshness [REQ]69%✓≥60% of references from 2025–2026. Current: 69%
[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 (65 × 60%) + Required (4/5 × 30%) + Optional (1/4 × 10%)
Spec-Driven AI Dev…Read More
Read more

XAI Interoperability Standards: How Explanation Formats Should Be Specified

Posted on by
Academic Research
Academic Research by Oleh Ivchenko  ·  DOI: 10.5281/zenodo.20026553  37stabilfr·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]2,366✓Minimum 2,000 words for a full research article. Current: 2,366
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.20026553
[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 (3/5 × 30%) + Optional (0/4 × 10%)

Explainable AI (XAI) systems generate explanations to justify model decisions, yet current standardization efforts lack coherent specifications for explanation formats. This article establishes a rigorous framework for XAI interoperability, defining mandatory components for explanation formats that ensure technical compatibility and functional validity across diverse deployment contexts. We ana...

Show moreHide
Academic Research by Oleh Ivchenko DOI: 10.5281/zenodo.20026553 37stabilfr·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]2,366✓Minimum 2,000 words for a full research article. Current: 2,366
[d]DOI [REQ]✓✓Zenodo DOI registered for persistent citation. DOI: 10.5281/zenodo.20026553
[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 (3/5 × 30%) + Optional (0/4 × 10%)
Spec-Driven AI Dev…Read More
Read more

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]DOI86%✓≥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 (71 × 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]DOI86%✓≥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 (71 × 60%) + Required (3/5 × 30%) + Optional (1/4 × 10%)
Spec-Driven AI Dev…Read More
Read more