Early-career researcher validating LLM synthetic samples for social-survey research
2
papers here
0
reviewed by Evolve
0
first-author
0
corresponding
—
works · OpenAlex
0
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—
Insufficient data. This axis would measure publication volume over time, but the OpenAlex record is too sparse to score: only 2 recent works are indexed under this name, and name ambiguity may understate true output.
Impact—
Insufficient data. This axis would measure citation-based influence such as per-work citations and h-index; the record reports h-index and i10-index of 0 with no further citation evidence, which is uninformative for a just-emerging profile.
Focus—
Insufficient data. This axis would measure topical concentration versus dispersion across a corpus; the record lists five distinct topic labels — from evolutionary psychology to authorship attribution — each attached to only one work, too fragmented to score.
Collaboration44/100
The collaboration axis scores 44. The OpenAlex record lists 8 distinct co-authors across the 2 recent works, and six partners recur in the network: Edoardo Chidichimo, Florian Kutzner, Celina Kacperski, Laura de Molière, Felix P. S. Wallis, and James K. He. Both catalogued papers are middle-authorship, non-corresponding contributions, so the score reflects participation in multi-author teams rather than independent leadership.
Activity32/100
The activity axis scores 32, reflecting a just-emerging record: all indexed output falls in 2026, with countsByYear showing exactly 2 works that year and recent3yWorks also equal to 2. No indexed works in earlier years are recorded, so this is an opening-year profile whose activity level could shift quickly as further work appears.
Reproducibility—
Insufficient data. This axis would measure code release, data availability, and replication readiness across the corpus; Evolve rates the two reviewed papers only medium and low on repro-readiness, too small a sample for a corpus-level score.
Research summary
Min Jun Jung is an early-stage researcher whose public bibliographic footprint, name-resolved via OpenAlex, currently centres on validating LLM-generated synthetic samples for social-survey research. The Evolve catalog holds two 2026 arXiv preprints with Jung as a middle author and not corresponding author. The first, the Artificial Societies Benchmark, proposes an 11-test scorecard validating LLM synthetic-survey research against 20 human sources and 9 models; Evolve finds the design credible but cautions that key cells rest on single generations. The second, 'Consequential Behaviour and Representational Fairness in the Validation of Synthetic Research,' argues — as yet without empirical testing — that synthetic samples be validated against real behaviour and subgroups; Evolve notes it comes from an industry vendor. Both works sit in computational social science and NLP evaluation, touching silicon sampling, persona simulation, psychometric validity, measurement invariance, and subgroup fairness. The quantitative record is thin: h-index and i10-index are 0, all indexed output (2 works) falls in 2026, and 8 distinct co-authors are recorded, giving radar scores of 32 for activity and 44 for collaboration, while output, impact, focus, and reproducibility lack sufficient data. The sparse, heterogeneous topic trail — five topics with one work each — argues for reading this profile with name-resolution caution.
Collaboration pattern
Both catalogued works are multi-author arXiv papers with Jung in a middle, non-corresponding position, consistent with a modest collaboration score of 44. OpenAlex records 8 distinct co-authors, and six partners recur: Edoardo Chidichimo, Florian Kutzner, Celina Kacperski, Laura de Molière, Felix P. S. Wallis, and James K. He. The pattern suggests contribution within an established synthetic-methods team rather than independent group leadership.
Research keywords
Highlights
An 11-test scorecard for LLM synthetic-survey research
A case for behavioural and subgroup validation of synthetic samples
Timeline
- 2026Co-authored the Artificial Societies Benchmark (arXiv), an 11-test validation framework for LLM synthetic-survey research evaluated across 20 human sources and 9 models.
- 2026Co-authored Consequential Behaviour and Representational Fairness in the Validation of Synthetic Research (arXiv), urging behavioural and subgroup validation of LLM synthetic samples.
- 2026OpenAlex-recorded output reached 2 works in 2026 with 8 distinct co-authors, while h-index and i10-index stand at 0 as the record emerges.
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 figures come from OpenAlex only; h-index and i10-index are both 0, and the profile is name-resolved from public bibliographic data.
- No institution, country, or ORCID is available, so identity may be ambiguous if Min Jun Jung is a shared name.
- Scope covers 2 works (2026 arXiv preprints); no peer-reviewed publications, citation history, or funding data are captured.
- Raw topic labels are heterogeneous (five topics, one work each), so the field assignment is a best-effort reading rather than a confirmed classification.