Applied mathematician: measure transport and generative modeling for Bayesian inverse problems and scientific ML
2
papers here
2
reviewed by Evolve
1
first-author
0
corresponding
—
works · OpenAlex
7
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-10-14) 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—
No score yet — the underlying publication-volume data is insufficient. This axis would measure cumulative research output: works per year, venue distribution, and preprint activity, once a more complete bibliographic record is confirmed for this researcher.
Impact—
No score yet — citation-based evidence is insufficient. This axis would measure scholarly impact through citation counts, h-index relative to field and career stage, and uptake of the methods by other groups, pending verified citation records.
Focus0/100
Radar scores focus at 0/100, and the raw distribution explains why: fieldDist splits evenly at 0.5/0.5 between applied mathematics (measure transport, Bayesian inverse problems) and scientific machine learning, while indexed topics span five clusters — from Model Reduction and Neural Networks (22) and Gaussian Processes and Bayesian Inference (22) to Target Tracking and Data Fusion in Sensor Networks (13). The halves are methodologically linked, but recorded topical spread is broad.
Collaboration36/100
Collaboration scores 36/100 and rests on a small, deep co-author pool: only 5 distinct coauthors are linked to this profile. The recurring partners — Bamdad Hosseini, Alexander W. Hsu, Nicholas Geissler, Shreya Jha, and Benjamin Peherstorfer — bridge the mathematical-theory and scientific-ML halves of the work, suggesting output is co-driven by a compact repeat-collaborator group rather than broad networking.
Activity99/100
Activity is the strongest axis at 99/100. Recorded works per year climb from 2 (2017) and 2 each in 2018–2019, through 5 (2020) and 4 (2022), to 7 (2025) and 16 already in 2026, with 29 works across 2024–2026. The curve steepens rather than plateaus, consistent with intensive arXiv preprinting, including both 2026 catalog papers.
Reproducibility55/100
Reproducibility scores 55/100, computed from exactly 2 reviewed papers (reproMean 55), both rated medium readiness. The first-author function-space paper is theory-rich — including new Gaussian optimal-transport rank results — but ships no code or end-to-end baselines; the one-step generative surrogate paper compensates with four benchmark comparisons at one network-function evaluation per step, while its theory remains idealized. Code release is the clear gap.
Research summary
Ricardo Baptista, listed with the University of Toronto, works at the intersection of measure transport, Bayesian inverse problems, and scientific machine learning. The OpenAlex-based profile splits recorded activity evenly (0.5/0.5) between applied mathematics — measure transport and Bayesian inverse problems — and scientific machine learning. Indexed topic clusters are led by Model Reduction and Neural Networks (22) and Gaussian Processes and Bayesian Inference (22), with Markov Chains and Monte Carlo Methods (18) close behind. The dominant signal is productivity: works per year rise from 2 in 2017 to 16 already recorded in 2026, with 29 works across 2024–2026 and an activity score of 99/100; reported citation metrics remain modest (h-index 7, i10-index 4). Two 2026 arXiv papers reviewed by Evolve define the current agenda. A first-author paper on approximating measures on function spaces delivers strong low-dimensional measure-modification theory and new Gaussian optimal-transport rank results, though code and end-to-end baselines are missing. A middle-author paper builds one-step generative surrogate models via block-triangular joint drifting, achieving strong benchmark accuracy at one network-function evaluation per step. Collaboration is compact — 5 distinct coauthors, with repeat partners including Bamdad Hosseini and Benjamin Peherstorfer — and the reproducibility score of 55/100 (from 2 reviewed papers) points to released code as the main gap.
Collaboration pattern
Collaboration is compact and stable: only 5 distinct coauthors appear on the profile, and the frequent set — Bamdad Hosseini, Alexander W. Hsu, Nicholas Geissler, Shreya Jha, and Benjamin Peherstorfer — spans both the applied-mathematics and scientific-ML halves of the fieldDist split. The 36/100 score reflects depth over breadth: repeat partnerships with a small, theory-oriented group rather than large, rotating project teams.
Research keywords
Highlights
First-author theory: transport and truncation for measures on function spaces
One-step generative surrogates via block-triangular joint drifting
2026 output surge: 16 recorded works in a single year
The OpenAlex profile records 16 works already in 2026 — the highest annual count of the 2017–2026 span — contributing to 29 works over the last three years and an activity score of 99/100.
Timeline
- 2017Earliest works recorded in the OpenAlex profile (2 works; counts hold at 2 per year through 2019).
- 2020Output steps up to 5 recorded works, the highest annual count to that point.
- 20246 recorded works — the start of the current three-year run totaling 29 works (2024–2026).
- 20257 recorded works, then the highest annual count on record.
- 202616 works recorded so far, including both Evolve-reviewed arXiv papers: a first-author study of measure transport and truncation on function spaces and a middle-author paper on one-step generative surrogates.
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 counts, topics, and citation metrics (h-index 7, i10-index 4) come from an OpenAlex-based profile and may undercount publications and citations.
- The reproducibility score (55/100) is computed from only 2 Evolve-reviewed papers (reproMean 55, reproPapers 2), so it reflects a narrow sample.
- 'Ricardo Baptista' is a relatively common name; this profile is name-resolved from public bibliographic data (OpenAlex identity, ORCID 0000-0002-0421-890X).
- Affiliation metadata lists country as 'US' while the institution given is the University of Toronto; treat the location field as unverified.