Last-author causal ML researcher: climate-driven food insecurity and kernel-method optimization theory
3
papers here
3
reviewed by Evolve
0
first-author
0
corresponding
—
works · OpenAlex
—
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-10-15) 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 output metrics are available in the current snapshot: publication counts, venue lists, and cumulative totals were not provided, so this axis is unscored rather than low. It would measure the volume and cadence of the researcher's published output over time.
Impact—
Impact data such as citation counts, h-index, or venue influence are absent from the input, so no score is given. This axis would measure how widely the work is cited and the scholarly influence it exerts across the community.
Focus0/100
Focus scores 0, and the raw field distribution explains why: the three reviewed papers fall into exactly three distinct fields — causal machine learning for climate and food security, causal machine learning for food security and humanitarian research, and machine learning theory on optimization and kernel methods — each holding an equal 33.3% share. The portfolio is fully diversified rather than concentrated, combining applied causal food-security work with abstract optimization theory.
Collaboration48/100
Collaboration scores 46, based on 9 distinct coauthors recorded across the reviewed papers. The recurring collaborator list — including Jordi Cerdà-Bautista, Vasileios Sitokonstantinou, Gherardo Varando, Michele Ronco, and Duccio Piovani, among others — suggests a stable working group, while the mid-range score indicates moderate rather than extensive network breadth within the available data.
Activity—
Recent-activity signals — yearly publication rate, preprint cadence, or service roles — are not in the snapshot beyond the three 2026 preprints, so this axis is left unscored. It would measure the researcher's current research tempo and level of engagement.
Reproducibility70/100
Reproducibility is the strongest scored axis at 70, the mean across three assessed papers. The Brownian RKHS optimization-geometry paper rates high, backed by rigorous proofs and verification, while both applied causal papers — the ENSO price-spike study and the Somalia credit-access study — rate medium, reflecting Evolve's checks on transparency, identification, and refutation robustness.
Research summary
Gustau Camps-Valls is profiled here from Evolve's reviewed catalog, which contains three 2026 arXiv preprints, each with him in the last author position and none marked corresponding. The catalog splits evenly across three fields, each holding one third of the reviewed output: causal machine learning for climate and food security, causal machine learning for food security and humanitarian research, and machine learning theory on optimization and kernel methods. The two applied papers estimate causal effects on food insecurity — one applies double machine learning to test whether ENSO sensitivity regimes modulate price-spike effects across Africa, the other uses an X-Learner to study credit access in the Horn of Africa — while the third analyzes the optimization geometry of equivalent Brownian RKHS representations under gradient descent, SGD, and Adam. Evolve's reproducibility assessment averages 70 across the three papers (medium, medium, high), the strongest quantitative signal on the radar; collaboration scores 46 with 9 distinct coauthors recorded. Output, impact, and activity axes lack sufficient data to score. The verdicts are mixed: the DML design is judged sound but the key regime contrast is only marginally significant; the credit-access identification is called thin, with several refutation tests failing; and the theory paper is rated rigorous but of modest novelty.
Collaboration pattern
Across the three reviewed papers the author sits in the last position each time and is never marked corresponding, a pattern consistent with a senior authorship role. The radar records 9 distinct coauthors and a collaboration score of 46; frequent coauthors include Jordi Cerdà-Bautista, Vasileios Sitokonstantinou, Homer Durand, Gherardo Varando, Michele Ronco, Duccio Piovani, and José María Tárraga. The pattern suggests a compact, stable group spanning applied food-security causal work and kernel-method theory.
Research keywords
Highlights
Testing whether ENSO regimes modulate price-spike effects on food insecurity
Causal ML links credit access to food security in the Horn of Africa
Proof that equivalent Brownian RKHS coordinates separate Adam but not GD or SGD
Timeline
- 2026Last-author arXiv preprint applies double machine learning to test whether ENSO sensitivity regimes modulate price-spike effects on African food insecurity.
- 2026Last-author preprint estimates credit-access effects on food security in the Horn of Africa using an X-Learner causal model.
- 2026Last-author theory preprint analyzes the optimization geometry of equivalent Brownian RKHS representations under GD, SGD, and Adam.
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.
- All bibliometrics and radar scores derive from a small snapshot: 3 reviewed 2026 arXiv preprints; no citation counts, h-index, or venue data are included.
- Institution, country, and ORCID are not provided in the input; the profile is name-resolved from public bibliographic data only.
- Output, impact, and activity radar axes are unscored because the underlying data is insufficient, not because performance is zero.
- All three papers are arXiv preprints with no corresponding-author marking, so peer-reviewed status is not established in this data.