First-author researcher on trustworthy AI for railway applications, bridging robustness and functional-safety standards
1
papers here
1
reviewed by Evolve
1
first-author
0
corresponding
—
works · OpenAlex
—
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-09-20) and cover the author's entire public record, not just the papers listed here. Reproducibility signal comes from Evolve's own reviews.
Research profile
Output—
Output data is not yet available: this snapshot holds a single reviewed paper and no total publication count, so the axis is unscored. It would measure cumulative publication volume over time and the balance between position papers and experimental work.
Impact—
Impact cannot be scored: the input provides no citation counts, h-index or altmetrics for this researcher. This axis would measure how often the work is cited and its uptake in railway-safety and trustworthy-AI practice.
Focus100/100
The focus score is a perfect 100: every classified output in the catalog sits in a single field, "trustworthy AI for safety-critical transportation (railway)", accounting for 1 of 1 classified papers. This is extreme, single-track specialization within one application domain rather than spread across topics, though a one-paper base makes the measure easy to saturate.
Collaboration36/100
Collaboration scores 36 on a 0-100 scale, computed from 5 distinct coauthors in the available data. The recurring circle is small and stable: Vincent Lébé, Ricardo Da Silva Ribeiro Pereira, Johan Sundell, Kenza Jaoul Arnaud Saiah and Nenad Mijatović. The first-authored 2026 paper relied on this compact team rather than a wide or shifting co-author network.
Activity—
Activity data is insufficient: only one publication year (2026) is present, so annual output rate and publishing consistency across years cannot be computed. This axis would measure publishing cadence and sustained research engagement over time.
Reproducibility20/100
The reproducibility score of 20 is the mean over 1 assessed paper. That single reviewed work is a position paper rated "low" for reproducibility readiness: Evolve's verdict notes it maps robustness, ODD and explainability onto railway standards but supports its "ready to use" claim with no experiments, leaving artifacts and empirical validation as the visible gaps.
Research summary
Lefebvre Renard Clément is an early-documentation researcher working at the intersection of trustworthy artificial intelligence and safety-critical transportation, with a documented focus on railway applications. The Evolve catalog currently holds one reviewed paper: "Building Trust in Artificial Intelligence: A Necessity for Railway Applications" (arXiv, 2026), on which this researcher is first author. It is a position paper that maps robustness, operational design domains (ODD) and explainability onto railway functional-safety practice built around SIL levels, and frames adversarial examples and certified defenses as safety-assurance questions rather than generic benchmark issues. Evolve's verdict credits it as "a solid bridge" between machine-learning assurance and railway safety standards, while noting that no experiments back its "ready to use" claim — reflected in a low reproducibility-readiness rating (score 20, from one assessed paper). The bibliometric signals are narrow but pointed: all classified output falls in a single field, yielding a perfect focus score of 100, and the visible collaboration circle is compact at 5 distinct coauthors (collaboration score 36), including Vincent Lébé, Ricardo Da Silva Ribeiro Pereira, Johan Sundell, Kenza Jaoul Arnaud Saiah and Nenad Mijatović. Output, impact and activity metrics are not yet available in this snapshot.
Collaboration pattern
Co-authorship visible in the data is compact: 5 distinct coauthors, with Vincent Lébé, Ricardo Da Silva Ribeiro Pereira, Johan Sundell, Kenza Jaoul Arnaud Saiah and Nenad Mijatović recurring as frequent collaborators. The single catalogued paper is first-authored (not corresponding) and team-produced, consistent with a small, stable group working on railway-oriented trustworthy AI rather than a broad, shifting network.
Research keywords
Highlights
Bridging trustworthy AI and railway functional safety
Adversarial robustness framed as a certification question
A "solid bridge" whose readiness claim outruns its evidence
Timeline
- 2026First-authored position paper "Building Trust in Artificial Intelligence: A Necessity for Railway Applications" released via arXiv.
- 2026The paper maps robustness, operational design domains (ODD) and explainability onto railway functional-safety (SIL) standards.
- 2026Evolve reviewed the paper, rating reproducibility readiness low (score 20, based on one assessed paper).
Papers in the Evolve catalog
Frequent co-authors
About this profile
This profile is AI-structured by Evolve.Pub from public bibliographic data (OpenAlex) and Evolve's own paper reviews. It is not written or endorsed by the researcher unless the profile is claimed. Radar dimensions are computed from real bibliometrics with fixed formulas — raw figures are shown alongside; missing dimensions mean insufficient data, never zero. Errors? Claim the profile to correct or hide it.
- Bibliometric coverage is minimal: all quantitative signals derive from a single reviewed 2026 arXiv paper, and output, impact and activity scores are unavailable.
- No institutional affiliation, country or ORCID is provided; the profile is name-resolved from public bibliographic data for the reviewed paper.
- The reproducibility score (mean 20) reflects one assessed paper and may not represent the researcher's broader practice.
- The collaboration score (36) is computed from 5 distinct coauthors in the available snapshot and excludes any unobserved collaborations.