Vasileios Sitokonstantinou

Research profile

Research summary

Vasileios Sitokonstantinou is a researcher at Wageningen University & Research whose catalogued work sits at the intersection of causal machine learning and food-security research. The current Evolve catalog contains two 2026 arXiv preprints on which he appears as a middle author without a corresponding role. The first, 'Climate Variability Modulates the Impact of Price Spikes on Food Insecurity', applies double machine learning to test whether ENSO sensitivity regimes stratify price-spike effects on African food insecurity; Evolve's review judges the design sound while noting that the key regime contrast is only marginally significant. The second, 'Credit Access is Associated with Improved Food Security in the Horn of Africa', uses causal ML — including an X-Learner — to claim that credit access cuts food insecurity in Somalia by roughly 2%, with transparent framing but, per the reviewer, thin identification and several failed refutation tests. The field distribution splits evenly (0.5/0.5) between two adjacent labels — causal ML for climate and food security, and causal ML for food security / humanitarian research — producing a focus score of 0. Radar scores show collaboration at 44 (8 distinct coauthors) and reproducibility at 55 (mean over 2 papers, both medium readiness); output, impact and activity axes lack sufficient data. A recurring collaborator core — Gustau Camps-Valls, Gherardo Varando, Jordi Cerdà-Bautista, Michele Ronco and others — indicates work embedded within an established research group.

Research keywords

Highlights

• ENSO sensitivity regimes as moderators of price-spike impacts on food insecurity

  The 2026 arXiv preprint applies double machine learning to test whether climate variability, indexed by ENSO sensitivity regimes, stratifies the effect of price spikes on food insecurity in Africa. Evolve's review rates the DML design sound but cautions that the key regime contrast is only marginally significant, so the headline moderation claim awaits stronger evidence.

• Causal ML evidence that credit access tracks with better food security in the Horn of Africa

  Using causal machine learning — an X-Learner for average treatment effects with IPC classification outcomes — the paper claims credit access cuts food insecurity in Somalia by roughly 2%. Evolve finds the framing transparent but the identification thin, with several refutation tests failing; results should be read cautiously until replicated.

• A coherent causal-ML program on food security at medium reproducibility readiness

  Across both catalog entries, the research applies causal machine learning to food-security outcomes, splitting evenly between climate-food-security and humanitarian field labels. Both papers carry medium reproducibility readiness and an average Evolve reproducibility score of 55, reflecting sound methodology while key claims still need stronger identification and replication.

Timeline

1. 2026Co-authored (middle position, non-corresponding) the arXiv preprint 'Climate Variability Modulates the Impact of Price Spikes on Food Insecurity', a double machine learning study of ENSO-stratified price-spike effects on African food insecurity.
2. 2026Co-authored (middle position, non-corresponding) the arXiv preprint 'Credit Access is Associated with Improved Food Security in the Horn of Africa', estimating credit-access effects on Somalia food insecurity with causal ML and an X-Learner.
3. 2026Both preprints entered the Evolve review catalog with medium reproducibility readiness (mean score 55 over 2 papers), within a collaborator network of 8 distinct coauthors.

Papers in the Evolve catalog

• 2026-09-21

  Climate Variability Modulates the Impact of Price Spikes on Food Insecurity

• 2026-09-21

  Credit Access is Associated with Improved Food Security in the Horn of Africa

Frequent co-authors