Machine-learning researcher linking brain-age prediction from fMRI to benchmark design for AI agent exploration
2
papers here
1
reviewed by Evolve
0
first-author
0
corresponding
—
works · OpenAlex
—
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-09-28) 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: the snapshot contains no publication counts, venue records, or authorship-volume data for this researcher. This axis would measure total scholarly output — how many papers, in which venues, and in what authorship roles over time.
Impact—
Not yet scored: no citation counts, h-index, or downstream-uptake measures are available in the provided data. This axis would gauge the influence of the work through citations and follow-on use by other researchers and subsequent studies.
Focus100/100
Focus scores 100, computed from a field distribution whose only labeled entry is computational neuroscience (ML for neuroimaging), weighted 1 — maximal concentration within this snapshot. The reviewed catalog adds a second line of work in LLM agent evaluation, so the perfect score reflects the labeled field data rather than an absence of breadth.
Collaboration68/100
Collaboration scores 68, with 29 distinct coauthors recorded and 12 recurring partners, including Ming Zhang, Zhenghao Xiang, Peizhong Gao, Yujiong Shen, Shihan Dou, and Junjie Ye. On both reviewed 2026 preprints Chen holds a middle, non-corresponding authorship position, a pattern consistent with steady contributing roles inside larger research teams rather than solo-led projects.
Activity—
Not yet scored: only 2026 preprint years are available, with no publication cadence or longitudinal career record. This axis would measure research activity over time — publication frequency, recency, and continuity across years.
Reproducibility55/100
Reproducibility scores 55 (reproMean), averaged over a single assessed paper (reproPapers = 1). Within the catalog, the brain-age RMCR paper carries medium reproducibility readiness, while ExplorationBench is rated low because three trajectories and single-run controls limit statistical strength. With only one paper behind the average, the score should be read as preliminary.
Research summary
Jiahao Chen is a researcher whose reviewed work to date spans two complementary strands of machine learning: statistical modeling of neuroimaging data and the evaluation of AI systems' exploratory behavior. On the first strand, the 2026 arXiv preprint 'Beyond Feature Reliability' proposes Repeat-Informed Multifractal Curve Regression (RMCR) for brain-age prediction from resting-state fMRI, combining multifractal analysis (MF-DFA) with repeat-informed regularization to improve test-retest reliability; Evolve's review notes reduced MAE/RAD relative to ridge regression, though without a significant edge over the strongest baselines. On the second strand, 'ExplorationBench' (2026) introduces a benchmark that measures AI systems' exploration in verifiable alien worlds using exact grading — a strong design, though the review flags that three trajectories and single-run controls limit statistical strength. Bibliometric indicators in scope show 29 distinct coauthors, a field distribution concentrated in computational neuroscience (ML for neuroimaging), a collaboration score of 68, a focus score of 100, and a reproducibility score of 55 averaged over one assessed paper. Both catalog papers list Chen as a middle-position, non-corresponding author, consistent with a contributing role within larger teams. Output, impact, and activity scores are not yet computable from the available snapshot. Because 'Jiahao Chen' is a common name, this profile is name-resolved from public bibliographic data.
Collaboration pattern
Chen's collaboration pattern is broad and team-based: the snapshot records 29 distinct coauthors, with 12 recurring partners including Ming Zhang, Zhenghao Xiang, Peizhong Gao, Yujiong Shen, Shihan Dou, and Junjie Ye. On both reviewed 2026 preprints Chen appears as a middle-position, non-corresponding author, indicating a contributor role within larger groups rather than a solo-led agenda. The recurring coauthor list points to sustained work with a stable core group.
Research keywords
Highlights
ExplorationBench: exact grading of AI exploration in alien worlds
RMCR: repeat-informed multifractal curve regression for brain-age prediction
Timeline
- 2026Co-authored the RMCR brain-age prediction preprint, combining MF-DFA multifractal curves with repeat-informed regularization for resting-state fMRI.
- 2026Co-authored ExplorationBench, an arXiv preprint introducing exact-graded evaluation of AI exploration in verifiable alien worlds.
- 2026Both reviewed works appeared within the same year, with Chen listed as a middle-position, non-corresponding author on each.
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.
- The name 'Jiahao Chen' is common; this profile is name-resolved from public bibliographic data and may merge or miss same-name records.
- Bibliometric scores come from a limited snapshot; institution, country, and ORCID are unavailable, so no affiliation-based disambiguation was possible.
- The reproducibility score averages a single assessed paper (reproPapers = 1); output, impact, and activity axes lack sufficient data to score.
- Only the two reviewed 2026 arXiv preprints are in scope; other work by this researcher is not reflected in this profile.