Machine learning researcher bridging time-series foundation models and differentiable optimization for energy systems
2
papers here
2
reviewed by Evolve
0
first-author
0
corresponding
—
works · OpenAlex
—
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-10-16) 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 measures total publication volume, authorship positions, and venue spread over time. The current snapshot contains only 2 arXiv preprints, both from 2026, which is insufficient to score this axis, so no output rating is given here.
Impact—
Impact would measure citation counts, citations per paper, and downstream uptake. No citation data is available in this snapshot — both papers are recent 2026 preprints — so this axis cannot be scored and is left unrated.
Focus0/100
The focus score is 0, and the underlying field distribution explains why: the two cataloged 2026 papers split evenly at 0.5 each between machine learning (time series forecasting) and energy systems and machine learning (differentiable optimization). With no field holding a majority share, the profile reads as a deliberate dual track rather than a concentrated single area.
Collaboration46/100
The collaboration score is 46, based on 9 distinct coauthors across the 2 cataloged papers. The frequent-coauthor list includes Maarten P. Scholl, Lucas Meyer, Claudio Sole, Huikan Xiang, Nicolas Li, Lucas Franceschino, Joachim Fainberg, Geoffrey Négiar, and Luca Mungo. Authorship positions — middle on the forecasting paper, last on the market-clearing paper, neither corresponding — indicate contributing roles within multi-author teams, consistent with the moderate score.
Activity—
Activity measures publishing cadence, such as papers per year and recency of output. With only two 2026 preprints and no multi-year publication record in the snapshot, there is not enough data to score this axis, so it remains unrated.
Reproducibility78/100
Reproducibility is the strongest measured dimension, with a mean readiness score of 78 computed across 2 papers. The open-weights t0 forecasting paper is rated high, backed by public benchmarks (GIFT-Eval, fev-bench), while the differentiable market-clearing paper is rated medium, with gradients validated only on two 12-bus toy grids. The 78 average signals a benchmark-driven, artifact-friendly style, though it rests on a very small sample.
Research summary
Arnau Quera-Bofarull (ORCID 0000-0001-5055-9863) is an early-career researcher whose Evolve catalog contains two 2026 arXiv preprints, split evenly between machine learning for time-series forecasting and energy systems with machine learning via differentiable optimization. The first, t0, reports open-weights time-series foundation models (t0-alpha and t0-beta); t0-beta ranks 3rd on GIFT-Eval/fev-bench and delivers probabilistic forecasting with covariates through quantile regression and transformer attention, earning Evolve's high repro-readiness rating. The second formulates electricity-market clearing as a differentiable layer for gradient-based data-center siting, validating implicit-differentiation gradients and achieving near-optimal solutions on two 12-bus test grids, though scale remains unproven. Bibliometrically, the profile records 9 distinct coauthors and a moderate collaboration score of 46, with authorship positions (middle and last, neither corresponding) pointing to team-based work; reproducibility is the strongest measured dimension, at a mean of 78 across 2 papers. Output, impact, and activity metrics are not yet available, and no institutional affiliation or country is recorded in the current data.
Collaboration pattern
Across the 2 catalog papers, 9 distinct coauthors appear — a set that coincides with the frequent-coauthor list: Maarten P. Scholl, Lucas Meyer, Claudio Sole, Huikan Xiang, Nicolas Li, Lucas Franceschino, Joachim Fainberg, Geoffrey Négiar, and Luca Mungo. The moderate collaboration score (46) matches this picture: multi-author arXiv work with middle and last authorship positions, neither corresponding, suggesting steady contribution within a stable, moderately sized team rather than wide-ranging external networks.
Research keywords
Highlights
Open-weights t0-beta ranks 3rd on GIFT-Eval / fev-bench
Probabilistic forecasting with covariates via quantile regression
Electricity-market clearing as a differentiable layer
Timeline
- 2026The paper 't0: A Time-Series Foundation Model for Forecasting with Context' appears on arXiv, with Quera-Bofarull in a middle authorship position.
- 2026The paper 'Differentiable Electricity-Market Clearing for Gradient-Based Planning' appears on arXiv, with Quera-Bofarull in the last authorship position.
- 2026Both catalog entries land in the same year, splitting the field distribution 50/50 and yielding a mean reproducibility score of 78 across the 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 are derived from a narrow snapshot: only 2 arXiv preprints (both 2026) in the Evolve catalog; output, impact, and activity dimensions lack sufficient underlying data.
- No institutional affiliation or country is recorded; the profile is name-resolved from public bibliographic data via ORCID 0000-0001-5055-9863.
- No citation counts, h-index, venue history, or career facts are provided in the input; none are inferred or estimated in this profile.
- The reproducibility mean of 78 covers only the 2 reviewed papers; per the Evolve verdict, the market-clearing method is validated only on two 12-bus toy grids, so its scale remains unproven.