Vanderbilt researcher formal-verifying neural networks and GNNs with reachability analysis and Star sets
2
papers here
2
reviewed by Evolve
0
first-author
0
corresponding
—
works · OpenAlex
—
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-10-02) 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—
Not yet scored: complete publication counts and output data are unavailable for this profile. This axis would measure the volume and cadence of papers, preprints, and verification artifacts over time.
Impact—
Not yet scored: citation counts, h-index, and uptake signals are absent from the current data. This axis would measure how widely the GNN verification work is cited and built upon by other researchers.
Focus0/100
Focus scores 0 on the radar, yet the raw field distribution splits only 50/50 between two adjacent labels — formal verification of machine learning and GNN verification for power systems — and both cataloged 2026 papers share reachability analysis and Star sets. The zero appears to reflect field-label granularity rather than genuinely scattered research interests.
Collaboration55/100
Collaboration scores 55, grounded in 15 distinct coauthors. Both 2026 papers list Wooding as a middle author rather than first or corresponding, indicating work within larger teams. Recurring partners include Taylor T. Johnson, Diego Manzanas Lopez, Anne M. Tumlin, Samuel Sasaki, Navid Hashemi, and Waseem Abbas — a network centered on neural network verification tooling at Vanderbilt.
Activity—
Not yet scored: recent-year publication and release activity is insufficient in the available data. This axis would measure current research tempo, such as new preprints, tool versions, and venue submissions in the most recent years.
Reproducibility100/100
Reproducibility scores 100, the radar's maximum, computed from a mean of 100 across the 2 papers with reproducibility data. Both 2026 preprints carry high reproducibility readiness, and NNV3 ships as a concrete MATLAB verification tool, supporting artifact-level reuse; the sample remains small at two papers.
Research summary
Ben Wooding is a researcher at Vanderbilt University working on the formal verification of machine learning, with a focus on reachability analysis and Star-set representations of neural networks. The Evolve catalog contains two 2026 arXiv preprints on which Wooding is a middle author. The first, on reachability-based formal verification of graph neural networks with node and edge features, claims the first edge-aware formal verification of GNNs through GraphStar sets and is applied to power systems; Evolve's review finds the method sound with a strong comparison against CORA, while flagging issues in PF feature design and selection. The second, NNV3, unifies weight-perturbation, video, GNN, probabilistic, and fairness verification in a single MATLAB tool; its integration is judged credible, though evaluations remain small. The bibliometric field distribution splits evenly between formal verification of machine learning and GNN verification for power systems — two adjacent labels within one specialty. Wooding has 15 distinct coauthors, including Taylor T. Johnson, Diego Manzanas Lopez, and Anne M. Tumlin, and both papers carry the catalog's highest reproducibility readiness (mean 100 across 2 papers). Output, impact, and activity metrics are not yet available for this profile; citation counts, h-index, and publication-volume data are therefore not quoted.
Collaboration pattern
Wooding's cataloged work is team-based: both 2026 papers list him as a middle, non-corresponding author. He has 15 distinct coauthors, with frequent partners including Taylor T. Johnson, Diego Manzanas Lopez, Anne M. Tumlin, Samuel Sasaki, Navid Hashemi, Waseem Abbas, Tyler Derr, and Meiyi Ma — a Vanderbilt-centered network around neural network verification tools. The radar's collaboration score is 55.
Research keywords
Highlights
First edge-aware formal verification of GNNs via GraphStar sets
NNV3: one MATLAB tool unifying five verification domains
Timeline
- 2026Posts reachability-based formal verification of graph neural networks with node and edge features to arXiv, claiming first edge-aware GNN verification via GraphStar sets.
- 2026Contributes as a middle author to NNV3, which unifies weight-perturbation, video, GNN, probabilistic, and fairness verification in one MATLAB tool.
- 2026Both cataloged papers receive Evolve's highest reproducibility readiness, yielding a reproducibility mean of 100 across 2 papers.
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 scores derive from OpenAlex-based radar data; the output, impact, and activity axes lack sufficient data and are left unscored.
- Coverage is limited to two 2026 arXiv preprints in the Evolve catalog; no peer-reviewed venue, citation, or h-index data is included.
- The profile is name-resolved via ORCID 0000-0003-1713-717X from public bibliographic data; no biographical facts beyond this scope are asserted.
- The timeline covers 2026 only; earlier career history falls outside the provided data.